Google’s Recommender System Breakthrough Detects Semantic Intent via @sejournal, @martinibuster

Google published a research paper about helping recommender systems understand what users mean when they interact with them. Their goal with this new approach is to overcome the limitations inherent in the current state-of-the-art recommender systems in order to get a finer, detailed understanding of what users want to read, listen to, or watch at the level of the individual.

Personalized Semantics

Recommender systems predict what a user would like to read or watch next. YouTube, Google Discover, and Google News are examples of recommender systems for recommending content to users. Other kinds of recommender systems are shopping recommendations.

Recommender systems generally work by collecting data about the kinds of things a user clicks on, rates, buys, and watches and then using that data to suggest more content that aligns with a user’s preferences.

The researchers referred to those kinds of signals as primitive user feedback because they’re not so good at recommendations based on an individual’s subjective judgment about what’s funny, cute, or boring.

The intuition behind the research is that the rise of LLMs presents an opportunity to leverage natural language interactions to better understand what a user wants through identifying semantic intent.

The researchers explain:

“Interactive recommender systems have emerged as a promising paradigm to overcome the limitations of the primitive user feedback used by traditional recommender systems (e.g., clicks, item consumption, ratings). They allow users to express intent, preferences, constraints, and contexts in a richer fashion, often using natural language (including faceted search and dialogue).

Yet more research is needed to find the most effective ways to use this feedback. One challenge is inferring a user’s semantic intent from the open-ended terms or attributes often used to describe a desired item. This is critical for recommender systems that wish to support users in their everyday, intuitive use of natural language to refine recommendation results.”

The Soft Attributes Challenge

The researchers explained that hard attributes are something that recommender systems can understand because they are objective ground truths like “genre, artist, director.” What they had problems with were other kinds of attributes called “soft attributes” that are subjective and for which they couldn’t be matched with movies, content, or product items.

The research paper states the following characteristics of soft attributes:

• “There is no definitive “ground truth” source associating such soft attributes with items
• The attributes themselves may have imprecise interpretations
• And they may be subjective in nature (i.e., different users may interpret them differently)”

The problem of soft attributes is the problem that the researchers set out to solve and why the research paper is called Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors.

Novel Use Of Concept Activation Vectors (CAVs)

Concept Activation Vectors (CAVs) are a way to probe AI models to understand the mathematical representations (vectors) the models use internally. They provide a way for humans to connect those internal vectors to concepts.

So the standard direction of the CAV is interpreting the model. What the researchers did was to change that direction so that the goal is now to interpret the users, translating subjective soft attributes into mathematical representations for recommender systems. The researchers discovered that adapting CAVs to interpret users enabled vector representations that helped AI models detect subtle intent and subjective human judgments that are personalized to an individual.

As they write:

“We demonstrate … that our CAV representation not only accurately interprets users’ subjective semantics, but can also be used to improve recommendations through interactive item critiquing.”

For example, the model can learn that users mean different things by “funny” and be better able to leverage those personalized semantics when making recommendations.

The problem the researchers are solving is figuring out how to bridge the semantic gap between how humans speak and how recommender systems “think.”

Humans think in concepts, using vague or subjective descriptions (called soft attributes).

Recommender systems “think” in math: They operate on vectors (lists of numbers) in a high-dimensional “embedding space”.

The problem then becomes making the subjective human speech less ambiguous but without having to modify or retrain the recommender system with all the nuances. The CAVs do that heavy lifting.

The researchers explain:

“…we infer the semantics of soft attributes using the representation learned by the recommender system model itself.”

They list four advantages of their approach:

“(1) The recommender system’s model capacity is directed to predicting user-item preferences without further trying to predict additional side information (e.g., tags), which often does not improve recommender system performance.

(2) The recommender system model can easily accommodate new attributes without retraining should new sources of tags, keywords or phrases emerge from which to derive new soft attributes.

(3) Our approach offers a means to test whether specific soft attributes are relevant to predicting user preferences. Thus, we are able focus attention on attributes most relevant to capturing a user’s intent (e.g., when explaining recommendations, eliciting preferences, or suggesting critiques).

(4) One can learn soft attribute/tag semantics with relatively small amounts of labelled data, in the spirit of pre-training and few-shot learning.”

They then provide a high-level explanation of how the system works:

“At a high-level, our approach works as follows. we assume we are given:

(i) a collaborative filtering-style model (e.g.,probabilistic matrix factorization or dual encoder) which embeds items and users in a latent space based on user-item ratings; and

(ii) a (small) set of tags (i.e., soft attribute labels) provided by a subset of users for a subset of items.

We develop methods that associate with each item the degree to which it exhibits a soft attribute, thus determining that attribute’s semantics. We do this by applying concept activation vectors (CAVs) —a recent method developed for interpretability of machine-learned models—to the collaborative filtering model to detect whether it learned a representation of the attribute.

The projection of this CAV in embedding space provides a (local) directional semantics for the attribute that can then be applied to items (and users). Moreover, the technique can be used to identify the subjective nature of an attribute, specifically, whether different users have different meanings (or tag senses) in mind when using that tag. Such a personalized semantics for subjective attributes can be vital to the sound interpretation of a user’s true intent when trying to assess her preferences.”

Does This System Work?

One of the interesting findings is that their test of an artificial tag (odd year) showed that the systems accuracy rate was barely above a random selection, which corroborated their hypothesis that “CAVs are useful for identifying preference related attributes/tags.”

They also found that using CAVs in recommender systems were useful for understanding “critiquing-based” user behavior and improved those kinds of recommender systems.

The researchers listed four benefits:

“(i) using a collaborative filtering representation to identify attributes of greatest relevance to the recommendation task;

(ii) distinguishing objective and subjective tag usage;

(iii) identifying personalized, user-specific semantics for subjective attributes; and

(iv) relating attribute semantics to preference representations, thus allowing interactions using soft attributes/tags in example critiquing and other forms of preference elicitation.”

They found that their approach improved recommendations for situations where discovery of soft attributes are important. Using this approach for situations in which hard attributes are more the norm, such as in product shopping, is a future area of study to see if soft attributes would aid in making product recommendations.

Takeaways

The research paper was published in 2024 and I had to dig around to actually find it, which may explain why it generally went unnoticed in the search marketing community.

Google tested some of this approach with an algorithm called WALS (Weighted Alternating Least Squares), actual production code that is a product in Google Cloud for developers.

Two notes in a footnote and in the appendix explain:

“CAVs on MovieLens20M data with linear attributes use embeddings that were learned (via WALS) using internal production code, which is not releasable.”

…The linear embeddings were learned (via WALS, Appendix A.3.1) using internal production code, which is not releasable.”

“Production code” refers to software that is currently running in Google’s user-facing products, in this case Google Cloud. It’s likely not the underlying engine for Google Discover, however it’s important to note because it shows how easily it can be integrated into an existing recommender system.

They tested this system using the MovieLens20M dataset, which is a public dataset of 20 million ratings, with some of the tests done with Google’s proprietary recommendation engine (WALS). This lends credibility to the inference that this code can be used on a live system without having to retrain or modify them.

The takeaway that I see in this research paper is that this makes it possible for recommender systems to leverage semantic data about soft attributes. Google Discover is regarded by Google as a subset of search, and search patterns are some of the data that the system uses to surface content. Google doesn’t say whether they are using this kind of method, but given the positive results, it is possible that this approach could be used in Google’s recommender systems. If that’s the case, then that means Google’s recommendations may be more responsive to users’ subjective semantics.

The research paper credits Google Research (60% of the credits), and also Amazon, Midjourney, and Meta AI.

The PDF is available here:

Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors

Featured Image by Shutterstock/Here

Google’s New Graph Foundation Model Catches Spam Up To 40x Better via @sejournal, @martinibuster

Google published details of a new kind of AI based on graphs called a Graph Foundation Model (GFM) that generalizes to previously unseen graphs and delivers a three to forty times boost in precision over previous methods, with successful testing in scaled applications such as spam detection in ads.

The announcement of this new technology is referred to as expanding the boundaries of what has been possible up to today:

“Today, we explore the possibility of designing a single model that can excel on interconnected relational tables and at the same time generalize to any arbitrary set of tables, features, and tasks without additional training. We are excited to share our recent progress on developing such graph foundation models (GFM) that push the frontiers of graph learning and tabular ML well beyond standard baselines.”

Graph Neural Networks Vs. Graph Foundation Models

Graphs are representations of data that are related to each other. The connections between the objects are called edges and the objects themselves are called nodes. In SEO, the most familiar type of graph could be said to be the Link Graph, which is a map of the entire web by the links that connect one web page to another.

Current technology uses Graph Neural Networks (GNNs) to represent data like web page content and can be used to identify the topic of a web page.

A Google Research blog post about GNNs explains their importance:

“Graph neural networks, or GNNs for short, have emerged as a powerful technique to leverage both the graph’s connectivity (as in the older algorithms DeepWalk and Node2Vec) and the input features on the various nodes and edges. GNNs can make predictions for graphs as a whole (Does this molecule react in a certain way?), for individual nodes (What’s the topic of this document, given its citations?)…

Apart from making predictions about graphs, GNNs are a powerful tool used to bridge the chasm to more typical neural network use cases. They encode a graph’s discrete, relational information in a continuous way so that it can be included naturally in another deep learning system.”

The downside to GNNs is that they are tethered to the graph on which they were trained and can’t be used on a different kind of graph. To use it on a different graph, Google has to train another model specifically for that other graph.

To make an analogy, it’s like having to train a new generative AI model on French language documents just to get it to work in another language, but that’s not the case because LLMs can generalize to other languages, which is not the case for models that work with graphs. This is the problem that the invention solves, to create a model that generalizes to other graphs without having to be trained on them first.

The breakthrough that Google announced is that with the new Graph Foundation Models, Google can now train a model that can generalize across new graphs that it hasn’t been trained on and understand patterns and connections within those graphs. And it can do it three to forty times more precisely.

Announcement But No Research Paper

Google’s announcement does not link to a research paper. It’s been variously reported that Google has decided to publish less research papers and this is a big example of that policy change. Is it because this innovation is so big they want to keep this as a competitive advantage?

How Graph Foundation Models Work

In a conventional graph, let’s say a graph of the Internet, web pages are the nodes. The links between the nodes (web pages) are called the edges. In that kind of graph, you can see similarities between pages because the pages about a specific topic tend to link to other pages about the same specific topic.

In very simple terms, a Graph Foundation Model turns every row in every table into a node and connects related nodes based on the relationships in the tables. The result is a single large graph that the model uses to learn from existing data and make predictions (like identifying spam) on new data.

Screenshot Of Five Tables

Image by Google

Transforming Tables Into A Single Graph

The research paper says this about the following images which illustrate the process:

“Data preparation consists of transforming tables into a single graph, where each row of a table becomes a node of the respective node type, and foreign key columns become edges between the nodes. Connections between five tables shown become edges in the resulting graph.”

Screenshot Of Tables Converted To Edges

Image by Google

What makes this new model exceptional is that the process of creating it is “straightforward” and it scales. The part about scaling is important because it means that the invention is able to work across Google’s massive infrastructure.

“We argue that leveraging the connectivity structure between tables is key for effective ML algorithms and better downstream performance, even when tabular feature data (e.g., price, size, category) is sparse or noisy. To this end, the only data preparation step consists of transforming a collection of tables into a single heterogeneous graph.

The process is rather straightforward and can be executed at scale: each table becomes a unique node type and each row in a table becomes a node. For each row in a table, its foreign key relations become typed edges to respective nodes from other tables while the rest of the columns are treated as node features (typically, with numerical or categorical values). Optionally, we can also keep temporal information as node or edge features.”

Tests Are Successful

Google’s announcement says that they tested it in identifying spam in Google Ads, which was difficult because it’s a system that uses dozens of large graphs. Current systems are unable to make connections between unrelated graphs and miss important context.

Google’s new Graph Foundation Model was able to make the connections between all the graphs and improved performance.

The announcement described the achievement:

“We observe a significant performance boost compared to the best tuned single-table baselines. Depending on the downstream task, GFM brings 3x – 40x gains in average precision, which indicates that the graph structure in relational tables provides a crucial signal to be leveraged by ML models.”

Is Google Using This System?

It’s notable that Google successfully tested the system with Google Ads for spam detection and reported upsides and no downsides. This means that it can be used in a live environment for a variety of real-world tasks. They used it for Google Ads spam detection and because it’s a flexible model that means it can be used for other tasks for which multiple graphs are used, from identifying content topics to identifying link spam.

Normally, when something falls short the research papers and announcement say that it points the way for future but that’s not how this new invention is presented. It’s presented as a success and it ends with a statement saying that these results can be further improved, meaning it can get even better than these already spectacular results.

“These results can be further improved by additional scaling and diverse training data collection together with a deeper theoretical understanding of generalization.”

Read Google’s announcement:

Graph foundation models for relational data

Featured Image by Shutterstock/SidorArt

Google’s Trust Ranking Patent Shows How User Behavior Is A Signal via @sejournal, @martinibuster

Google long ago filed a patent for ranking search results by trust. The groundbreaking idea behind the patent is that user behavior can be used as a starting point for developing a ranking signal.

The big idea behind the patent is that the Internet is full of websites all linking to and commenting about each other. But which sites are trustworthy? Google’s solution is to utilize user behavior to indicate which sites are trusted and then use the linking and content on those sites to reveal more sites that are trustworthy for any given topic.

PageRank is basically the same thing only it begins and ends with one website linking to another website. The innovation of Google’s trust ranking patent is to put the user at the start of that trust chain like this:

User trusts X Websites > X Websites trust Other Sites > This feeds into Google as a ranking signal

The trust originates from the user and flows to trust sites that themselves provide anchor text, lists of other sites and commentary about other sites.

That, in a nutshell, is what Google’s trust-based ranking algorithm is about.

The deeper insight is that it reveals Google’s groundbreaking approach to letting users be a signal of what’s trustworthy. You know how Google keeps saying to create websites for users? This is what the trust patent is all about, putting the user in the front seat of the ranking algorithm.

Google’s Trust And Ranking Patent

The patent was coincidentally filed around the same period that Yahoo and Stanford University published a Trust Rank research paper which is focused on identifying spam pages.

Google’s patent is not about finding spam. It’s focused on doing the opposite, identifying trustworthy web pages that satisfy the user’s intent for a search query.

How Trust Factors Are Used

The first part of any patent consists of an Abstract section that offers a very general description of the invention that that’s what this patent does as well.

The patent abstract asserts:

• That trust factors are used to rank web pages.
• The trust factors are generated from “entities” (which are later described to be the users themselves, experts, expert web pages, and forum members) that link to or comment about other web pages).
• Those trust factors are then used to re-rank web pages.
• Re-ranking web pages kicks in after the normal ranking algorithm has done its thing with links, etc.

Here’s what the Abstract says:

“A search engine system provides search results that are ranked according to a measure of the trust associated with entities that have provided labels for the documents in the search results.

A search engine receives a query and selects documents relevant to the query.

The search engine also determines labels associated with selected documents, and the trust ranks of the entities that provided the labels.

The trust ranks are used to determine trust factors for the respective documents. The trust factors are used to adjust information retrieval scores of the documents. The search results are then ranked based on the adjusted information retrieval scores.”

As you can see, the Abstract does not say who the “entities” are nor does it say what the labels are yet, but it will.

Field Of The Invention

The next part is called the Field Of The Invention. The purpose is to describe the technical domain of the invention (which is information retrieval) and the focus (trust relationships between users) for the purpose of ranking web pages.

Here’s what it says:

“The present invention relates to search engines, and more specifically to search engines that use information indicative of trust relationship between users to rank search results.”

Now we move on to the next section, the Background, which describes the problem this invention solves.

Background Of The Invention

This section describes why search engines fall short of answering user queries (the problem) and why the invention solves the problem.

The main problems described are:

• Search engines are essentially guessing (inference) what the user’s intent is when they only use the search query.
• Users rely on expert-labeled content from trusted sites (called vertical knowledge sites) to tell them which web pages are trustworthy
• Explains why the content labeled as relevant or trustworthy is important but ignored by search engines.
• It’s important to remember that this patent came out before the BERT algorithm and other natural language approaches that are now used to better understand search queries.

This is how the patent explains it:

“An inherent problem in the design of search engines is that the relevance of search results to a particular user depends on factors that are highly dependent on the user’s intent in conducting the search—that is why they are conducting the search—as well as the user’s circumstances, the facts pertaining to the user’s information need.

Thus, given the same query by two different users, a given set of search results can be relevant to one user and irrelevant to another, entirely because of the different intent and information needs.”

Next it goes on to explain that users trust certain websites that provide information about certain topics:

“…In part because of the inability of contemporary search engines to consistently find information that satisfies the user’s information need, and not merely the user’s query terms, users frequently turn to websites that offer additional analysis or understanding of content available on the Internet.”

Websites Are The Entities

The rest of the Background section names forums, review sites, blogs, and news websites as places that users turn to for their information needs, calling them vertical knowledge sites. Vertical Knowledge sites, it’s explained later, can be any kind of website.

The patent explains that trust is why users turn to those sites:

“This degree of trust is valuable to users as a way of evaluating the often bewildering array of information that is available on the Internet.”

To recap, the “Background” section explains that the trust relationships between users and entities like forums, review sites, and blogs can be used to influence the ranking of search results. As we go deeper into the patent we’ll see that the entities are not limited to the above kinds of sites, they can be any kind of site.

Patent Summary Section

This part of the patent is interesting because it brings together all of the concepts into one place, but in a general high-level manner, and throws in some legal paragraphs that explain that the patent can apply to a wider scope than is set out in the patent.

The Summary section appears to have four sections:

• The first section explains that a search engine ranks web pages that are trusted by entities (like forums, news sites, blogs, etc.) and that the system maintains information about these labels about trusted web pages.
• The second section offers a general description of the work of the entities (like forums, news sites, blogs, etc.).
• The third offers a general description of how the system works, beginning with the query, the assorted hand waving that goes on at the search engine with regard to the entity labels, and then the search results.
• The fourth part is a legal explanation that the patent is not limited to the descriptions and that the invention applies to a wider scope. This is important. It enables Google to use a non-existent thing, even something as nutty as a “trust button” that a user selects to identify a site as being trustworthy as an example. This enables an example like a non-existent “trust button” to be a stand-in for something else, like navigational queries or Navboost or anything else that is a signal that a user trusts a website.

Here’s a nutshell explanation of how the system works:

• The user visits sites that they trust and click a “trust button” that tells the search engine that this is a trusted site.
• The trusted site “labels” other sites as trusted for certain topics (the label could be a topic like “symptoms”).
• A user asks a question at a search engine (a query) and uses a label (like “symptoms”).
• The search engine ranks websites according to the usual manner then it looks for sites that users trust and sees if any of those sites have used labels about other sites.
• Google ranks those other sites that have had labels assigned to them by the trusted sites.

Here’s an abbreviated version of the third part of the Summary that gives an idea of the inner workings of the invention:

“A user provides a query to the system…The system retrieves a set of search results… The system determines which query labels are applicable to which of the search result documents. … determines for each document an overall trust factor to apply… adjusts the …retrieval score… and reranks the results.”

Here’s that same section in its entirety:

• “A user provides a query to the system; the query contains at least one query term and optionally includes one or more labels of interest to the user.
• The system retrieves a set of search results comprising documents that are relevant to the query term(s).
• The system determines which query labels are applicable to which of the search result documents.
• The system determines for each document an overall trust factor to apply to the document based on the trust ranks of those entities that provided the labels that match the query labels.
• Applying the trust factor to the document adjusts the document’s information retrieval score, to provide a trust adjusted information retrieval score.
• The system reranks the search result documents based at on the trust adjusted information retrieval scores.”

The above is a general description of the invention.

The next section, called Detailed Description, deep dives into the details. At this point it’s becoming increasingly evident that the patent is highly nuanced and can not be reduced to simple advice similar to: “optimize your site like this to earn trust.”

A large part of the patent hinges on a trust button and an advanced search query:  label:

Neither the trust button or the label advanced search query have ever existed. As you’ll see, they are quite probably stand-ins for techniques that Google doesn’t want to explicitly reveal.

Detailed Description In Four Parts

The details of this patent are located in four sections within the Detailed Description section of the patent. This patent is not as simple as 99% of SEOs say it is.

These are the four sections:

1. System Overview
2. Obtaining and Storing Trust Information
3. Obtaining and Storing Label Information
4. Generated Trust Ranked Search Results

The System Overview is where the patent deep dives into the specifics. The following is an overview to make it easy to understand.

System Overview

1. Explains how the invention (a search engine system) ranks search results based on trust relationships between users and the user-trusted entities who label web content.

2. The patent describes a “trust button” that a user can click that tells Google that a user trusts a website or trusts the website for a specific topic or topics.

3. The patent says a trust related score is assigned to a website when a user clicks a trust button on a website.

4. The trust button information is stored in a trust database that’s referred to as #190.

Here’s what it says about assigning a trust rank score based on the trust button:

“The trust information provided by the users with respect to others is used to determine a trust rank for each user, which is measure of the overall degree of trust that users have in the particular entity.”

Trust Rank Button

The patent refers to the “trust rank” of the user-trusted websites. That trust rank is based on a trust button that a user clicks to indicate that they trust a given website, assigning a trust rank score.

The patent says:

“…the user can click on a “trust button” on a web page belonging to the entity, which causes a corresponding record for a trust relationship to be recorded in the trust database 190.

In general any type of input from the user indicating that such as trust relationship exists can be used.”

The trust button has never existed and the patent quietly acknowledges this by stating that any type of input can be used to indicate the trust relationship.

So what is it? I believe that the “trust button” is a stand-in for user behavior metrics in general, and site visitor data in particular. The patent Claims section does not mention trust buttons at all but does mention user visitor data as an indicator of trust.

Here are several passages that mention site visits as a way to understand if a user trusts a website:

“The system can also examine web visitation patterns of the user and can infer from the web visitation patterns which entities the user trusts. For example, the system can infer that a particular user trust a particular entity when the user visits the entity’s web page with a certain frequency.”

The same thing is stated in the Claims section of the patent, it’s the very first claim they make for the invention:

“A method performed by data processing apparatus, the method comprising:
determining, based on web visitation patterns of a user, one or more trust relationships indicating that the user trusts one or more entities;”

It may very well be that site visitation patterns and other user behaviors are what is meant by the “trust button” references.

Labels Generated By Trusted Sites

The patent defines trusted entities as news sites, blogs, forums, and review sites, but not limited to those kinds of sites, it could be any other kind of website.

Trusted websites create references to other sites and in that reference they label those other sites as being relevant to a particular topic. That label could be an anchor text. But it could be something else.

The patent explicitly mentions anchor text only once:

“In some cases, an entity may simply create a link from its site to a particular item of web content (e.g., a document) and provide a label 107 as the anchor text of the link.”

Although it only explicitly mentions anchor text once, there are other passages where it anchor text is strongly implied, for example, the patent offers a general description of labels as describing or categorizing the content found on another site:

“…labels are words, phrases, markers or other indicia that have been associated with certain web content (pages, sites, documents, media, etc.) by others as descriptive or categorical identifiers.”

Labels And Annotations

Trusted sites link out to web pages with labels and links. The combination of a label and a link is called an annotation.

This is how it’s described:

“An annotation 106 includes a label 107 and a URL pattern associated with the label; the URL pattern can be specific to an individual web page or to any portion of a web site or pages therein.”

Labels Used In Search Queries

Users can also search with “labels” in their queries by using a non-existent “label:” advanced search query. Those kinds of queries are then used to match the labels that a website page is associated with.

This is how it’s explained:

“For example, a query “cancer label:symptoms” includes the query term “cancel” and a query label “symptoms”, and thus is a request for documents relevant to cancer, and that have been labeled as relating to “symptoms.”

Labels such as these can be associated with documents from any entity, whether the entity created the document, or is a third party. The entity that has labeled a document has some degree of trust, as further described below.”

What is that label in the search query? It could simply be certain descriptive keywords, but there aren’t any clues to speculate further than that.

The patent puts it all together like this:

“Using the annotation information and trust information from the trust database 190, the search engine 180 determines a trust factor for each document.”

Takeaway:

A user’s trust is in a website. That user-trusted website is not necessarily the one that’s ranked, it’s the website that’s linking/trusting another relevant web page. The web page that is ranked can be the one that the trusted site has labeled as relevant for a specific topic and it could be a web page in the trusted site itself. The purpose of the user signals is to provide a starting point, so to speak, from which to identify trustworthy sites.

Experts Are Trusted

Vertical Knowledge Sites, sites that users trust, can host the commentary of experts. The expert could be the publisher of the trusted site as well. Experts are important because links from expert sites are used as part of the ranking process.

Experts are defined as publishing a deep level of content on the topic:

“These and other vertical knowledge sites may also host the analysis and comments of experts or others with knowledge, expertise, or a point of view in particular fields, who again can comment on content found on the Internet.

For example, a website operated by a digital camera expert and devoted to digital cameras typically includes product reviews, guidance on how to purchase a digital camera, as well as links to camera manufacturer’s sites, new products announcements, technical articles, additional reviews, or other sources of content.

To assist the user, the expert may include comments on the linked content, such as labeling a particular technical article as “expert level,” or a particular review as “negative professional review,” or a new product announcement as ;new 10MP digital SLR’.”

Links From Expert Sites

Links and annotations from user-trusted expert sites are described as sources of trust information:

“For example, Expert may create an annotation 106 including the label 107 “Professional review” for a review 114 of Canon digital SLR camera on a web site “www.digitalcameraworld.com”, a label 107 of “Jazz music” for a CD 115 on the site “www.jazzworld.com”, a label 107 of “Classic Drama” for the movie 116 “North by Northwest” listed on website “www.movierental.com”, and a label 107 of “Symptoms” for a group of pages describing the symptoms of colon cancer on a website 117 “www.yourhealth.com”.

Note that labels 107 can also include numerical values (not shown), indicating a rating or degree of significance that the entity attaches to the labeled document.

Expert’s web site 105 can also include trust information. More specifically, Expert’s web site 105 can include a trust list 109 of entities whom Expert trusts. This list may be in the form of a list of entity names, the URLs of such entities’ web pages, or by other identifying information. Expert’s web site 105 may also include a vanity list 111 listing entities who trust Expert; again this may be in the form of a list of entity names, URLs, or other identifying information.”

Inferred Trust

The patent describes additional signals that can be used to signal (infer) trust. These are more traditional type signals like links, a list of trusted web pages (maybe a resources page?) and a list of sites that trust the website.

These are the inferred trust signals:

“(1) links from the user’s web page to web pages belonging to trusted entities;
(2) a trust list that identifies entities that the user trusts; or
(3) a vanity list which identifies users who trust the owner of the vanity page.”

Another kind of trust signal that can be inferred is from identifying sites that a user tends to visit.

The patent explains:

“The system can also examine web visitation patterns of the user and can infer from the web visitation patterns which entities the user trusts. For example, the system can infer that a particular user trusts a particular entity when the user visits the entity’s web page with a certain frequency.”

Takeaway:

That’s a pretty big signal and I believe that it suggests that promotional activities that encourage potential site visitors to discover a site and then become loyal site visitors can be helpful. For example, that kind of signal can be tracked with branded search queries. It could be that Google is only looking at site visit information but I think that branded queries are an equally trustworthy signal, especially when those queries are accompanied by labels… ding, ding, ding!

The patent also lists some kind of out there examples of inferred trust like contact/chat list data. It doesn’t say social media, just contact/chat lists.

Trust Can Decay or Increase

Another interesting feature of trust rank is that it can decay or increase over time.

The patent is straightforward about this part:

“Note that trust relationships can change. For example, the system can increase (or decrease) the strength of a trust relationship for a trusted entity. The search engine system 100 can also cause the strength of a trust relationship to decay over time if the trust relationship is not affirmed by the user, for example by visiting the entity’s web site and activating the trust button 112.”

Trust Relationship Editor User Interface

Directly after the above paragraph is a section about enabling users to edit their trust relationships through a user interface. There has never been such a thing, just like the non-existent trust button.

This is possibly a stand-in for something else. Could this trusted sites dashboard be Chrome browser bookmarks or sites that are followed in Discover? This is a matter for speculation.

Here’s what the patent says:

“The search engine system 100 may also expose a user interface to the trust database 190 by which the user can edit the user trust relationships, including adding or removing trust relationships with selected entities.

The trust information in the trust database 190 is also periodically updated by crawling of web sites, including sites of entities with trust information (e.g., trust lists, vanity lists); trust ranks are recomputed based on the updated trust information.”

What Google’s Trust Patent Is About

Google’s Search Result Ranking Based On Trust patent describes a way of leveraging user-behavior signals to understand which sites are trustworthy. The system then identifies sites that are trusted by the user-trusted sites and uses that information as a ranking signal. There is no actual trust rank metric, but there are ranking signals related to what users trust. Those signals can decay or increase based on factors like whether a user still visits those sites.

The larger takeaway is that this patent is an example of how Google is focused on user signals as a ranking source, so that they can feed that back into ranking sites that meet their needs. This means that instead of doing things because “this is what Google likes,” it’s better to go even deeper and do things because users like it. That will feed back to Google through these kinds of algorithms that measure user behavior patterns, something we all know Google uses.

Featured Image by Shutterstock/samsulalam

Google Files Patent On Personal History-Based Search via @sejournal, @martinibuster

Google recently filed a patent for a way to provide search results based on a user’s browsing and email history. The patent outlines a new way to search within the context of a search engine, within an email interface, and through a voice-based assistant (referred to in the patent as a voice-based dialog system).

A problem that many people have is that they can remember what they saw but they can’t remember where they saw it or how they found it. The new patent, titled Generating Query Answers From A User’s History, solves that problem by helping people find information they’ve previously seen within a webpage or an email by enabling them to ask for what they’re looking for using everyday language such as “What was that article I read last week about chess?”

The problem the invention solves is that traditional search engines don’t enable users to easily search their own browsing or email history using natural language. The invention works by taking a user’s spoken or typed question, recognizing that the question is asking for previously viewed content, and then retrieving search results from the user’s personal history (such as their browser history or emails). In order to accomplish this it uses filters like date, topic, or device used.

What’s novel about the invention is the system’s ability to understand vague or fuzzy natural language queries and match them to a user’s specific past interactions, including showing the version of a page as it looked when the user originally saw it (a cached version of the web page).

Query Classification (Intent) And Filtering

Query Classification

The system first determines whether the intent of the user’s spoken or typed query is to retrieve previously accessed information. This process is called query classification and involves analyzing the phrasing of the query to detect the intent. The system compares parts of the query to known patterns associated with history-seeking questions and uses techniques like semantic analysis and similarity thresholds to identify if the user’s intent is to seek something they’d seen before, even when the wording is vague or conversational.

The similarity threshold is an interesting part of the invention because it compares what the user is saying or typing to known history-seeking phrases to see if they are similar. It’s not looking for an exact match but rather a close match.

Filtering

The next part is filtering, and it happens after the system has identified the history-seeking intent. It then applies filters such as the topic, time, or device to limit the search to content from the user’s personal history that matches those criteria.

The time filter is a way to constrain the search to within a specific time frame that’s mentioned or implied in the search query. This helps the system narrow down the search results to what the user is trying to find. So if a user speaks phrases like “last week” or “a few days ago” then it knows to restrict the query to those respective time frames.

An interesting quality of the time filter is that it’s applied with a level of fuzziness, which means it’s not exact. So when a person asks the voice assistant to find something from the past week it won’t do a literal search of the past seven days but will expand it to a longer period of time.

The patent describes the fuzzy quality of the time filter:

“For example, the browser history collection… may include a list of web pages that were accessed by the user. The search engine… may obtain documents from the index… based on the filters from the formatted query.

For example, if the formatted query… includes a date filter (e.g., “last week”) and a topic filter (e.g., “chess story”), the search engine… may retrieve only documents from the collection… that satisfy these filters, i.e., documents that the user accessed in the previous week that relate to a “chess story.”

In this example, the search engine… may apply fuzzy time ranges to the “last week” filter to account for inaccuracies in human memory. In particular, while “last week” literally refers to the seven calendar days of the previous week, the search engine… may search for documents over a wider range, e.g., anytime in the past two weeks.”

Once a query is classified as asking for something that was previously seen, the system identifies details in the user’s phrasing that are indicative of topic, date or time, source, device, sender, or location and uses them as filters to search the user’s personal history.

Each filter helps narrow the scope of the search to match what the user is trying to recall: for example, a topic filter (“turkey recipe”) targets the subject of the content; a time filter (“last week”) restricts results to when it was accessed; a source filter (“WhiteHouse.gov”) limits the search to specific websites; a device filter (e.g., “on my phone”) further restricts the search results from a certain device; a sender filter (“from grandma”) helps locate emails or shared content; and a location filter (e.g., “at work”) restricts results to those accessed in a particular physical place.

By combining these context-sensitive filters, the system mimics the way people naturally remember content in order to help users retrieve exactly what they’re looking for, even when their query is vague or incomplete.

Scope of Search: What Is Searched

The next part of the patent is about figuring out the scope of what is going to be searched, which is limited to predefined sources such as browser history, cached versions of web pages, or emails. So, rather than searching the entire web, the system focuses only on the user’s personal history, making the results more relevant to what the user is trying to recall.

Cached Versions of Previously Viewed Content

Another interesting feature described in the patent is web page caching. Caching refers to saving a copy of a web page as it appeared when the user originally viewed it. This enables the system to show the user that specific version of the page in search results, rather than the current version, which may have changed or been removed.

The cached version acts like a snapshot in time, making it easier for the user to recognize or remember the content they are looking for. This is especially useful when the user doesn’t remember precise details like the name of the page or where they found it, but would recognize it if they saw it again. By showing the version that the user actually saw, the system makes the search experience more aligned with how people remember things.

Potential Applications Of The Patent Invention

The system described in the patent can be applied in several real-world contexts where users may want to retrieve content they’ve previously seen:

Search Engines

The patent refers multiple times to the use of this technique in the context of a search engine that retrieves results not from the public web, but from the user’s personal history, such as previously visited web pages and emails. While the system is designed to search only content the user has previously accessed, the patent notes that some implementations may also include additional documents relevant to the query, even if the user hasn’t viewed them before.

Email Clients

The system treats previously accessed emails as part of the searchable history. For example, it can return an old email like “Grandma’s turkey meatballs” based on vague, natural language queries.

Voice Assistants

The patent includes examples of “a voice-based search” where users speak conversational queries like “I’m looking for a turkey recipe I read on my phone.” The system handles speech recognition and interprets intent to retrieve relevant results from personal history.

Read the entire patent here:

Generating query answers from a user’s history

Google’s New Infini-Attention And SEO via @sejournal, @martinibuster

Google has published a research paper on a new technology called Infini-attention that allows it to process massively large amounts of data with “infinitely long contexts” while also being capable of being easily inserted into other models to vastly improve their capabilities

That last part should be of interest to those who are interested in Google’s algorithm. Infini-Attention is plug-and-play, which means it’s relatively easy to insert into other models, including those in use b Google’s core algorithm. The part about “infinitely long contexts” may have implications for how some of Google’s search systems may work.

The name of the research paper is: Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Memory Is Computationally Expensive For LLMs

Large Language Models (LLM) have limitations on how much data they can process at one time because the computational complexity and memory usage can spiral upward significantly. Infini-Attention gives the LLM the ability to handle longer contexts while keeping the down memory and processing power needed.

The research paper explains:

“Memory serves as a cornerstone of intelligence, as it enables efficient computations tailored to specific contexts. However, Transformers …and Transformer-based LLMs …have a constrained context-dependent memory, due to the nature of the attention mechanism.

Indeed, scaling LLMs to longer sequences (i.e. 1M tokens) is challenging with the standard Transformer architectures and serving longer and longer context models becomes costly financially.”

And elsewhere the research paper explains:

“Current transformer models are limited in their ability to process long sequences due to quadratic increases in computational and memory costs. Infini-attention aims to address this scalability issue.”

The researchers hypothesized that Infini-attention can scale to handle extremely long sequences with Transformers without the usual increases in computational and memory resources.

Three Important Features

Google’s Infini-Attention solves the shortcomings of transformer models by incorporating three features that enable transformer-based LLMs to handle longer sequences without memory issues and use context from earlier data in the sequence, not just data near the current point being processed.

The features of Infini-Attention

• Compressive Memory System
• Long-term Linear Attention
• Local Masked Attention

Compressive Memory System

Infini-Attention uses what’s called a compressive memory system. As more data is input (as part of a long sequence of data), the compressive memory system compresses some of the older information in order to reduce the amount of space needed to store the data.

Long-term Linear Attention

Infini-attention also uses what’s called, “long-term linear attention mechanisms” which enable the LLM to process data that exists earlier in the sequence of data that’s being processed which enables to retain the context. That’s a departure from standard transformer-based LLMs.

This is important for tasks where the context exists on a larger plane of data. It’s like being able to discuss and entire book and all of the chapters and explain how the first chapter relates to another chapter closer to the end of the book.

Local Masked Attention

In addition to the long-term attention, Infini-attention also uses what’s called local masked attention. This kind of attention processes nearby (localized) parts of the input data, which is useful for responses that depend on the closer parts of the data.

Combining the long-term and local attention together helps solve the problem of transformers being limited to how much input data it can remember and use for context.

The researchers explain:

“The Infini-attention incorporates a compressive memory into the vanilla attention mechanism and builds in both masked local attention and long-term linear attention mechanisms in a single Transformer block.”

Results Of Experiments And Testing

Infini-attention was tested with other models for comparison across multiple benchmarks involving long input sequences, such as long-context language modeling, passkey retrieval, and book summarization tasks. Passkey retrieval is a test where the language model has to retrieve specific data from within a extremely long text sequence.

List of the three tests:

1. Long-context Language Modeling
2. Passkey Test
3. Book Summary

Long-Context Language Modeling And The Perplexity Score

The researchers write that the Infini-attention outperformed the baseline models and that increasing the training sequence length brought even further improvements in the Perplexity score. The Perplexity score is a metric that measures language model performance with lower scores indicating better performance.

The researchers shared their findings:

“Infini-Transformer outperforms both Transformer-XL …and Memorizing Transformers baselines while maintaining 114x less memory parameters than the Memorizing Transformer model with a vector retrieval-based KV memory with length of 65K at its 9th layer. Infini-Transformer outperforms memorizing transformers with memory length of 65K and achieves 114x compression ratio.

We further increased the training sequence length to 100K from 32K and trained the models on Arxiv-math dataset. 100K training further decreased the perplexity score to 2.21 and 2.20 for Linear and Linear + Delta models.”

Passkey Test

The passkey test is wherea random number is hidden within a long text sequence with the task being that the model must fetch the hidden text. The passkey is hidden either near the beginning, middle or the end of the long text. The model was able to solve the passkey test up to a length of 1 million.

“A 1B LLM naturally scales to 1M sequence length and solves the passkey retrieval task when injected with Infini-attention. Infini-Transformers solved the passkey task with up to 1M context length when fine-tuned on 5K length inputs. We report token-level retrieval accuracy for passkeys hidden in a different part (start/middle/end) of long inputs with lengths 32K to 1M.”

Book Summary Test

Infini-attention also excelled at the book summary test by outperforming top benchmarks achieving new state of the art (SOTA) performance levels.

The results are described:

“Finally, we show that a 8B model with Infini-attention reaches a new SOTA result on a 500K length book summarization task after continual pre-training and task fine-tuning.

…We further scaled our approach by continuously pre-training a 8B LLM model with 8K input length for 30K steps. We then fine-tuned on a book summarization task, BookSum (Kry´sci´nski et al., 2021) where the goal is to generate a summary of an entire book text.

Our model outperforms the previous best results and achieves a new SOTA on BookSum by processing the entire text from book. …There is a clear trend showing that with more text provided as input from books, our Infini-Transformers improves its summarization performance metric.”

Implications Of Infini-Attention For SEO

Infini-attention is a breakthrough in modeling long and short range attention with greater efficiency than previous models without Infini-attention. It also supports “plug-and-play continual pre-training and long-context adaptation
by design” which means that it can easily be integrated into existing models.

Lastly, the “continual pre-training and long-context adaptation” makes it exceptionally useful for scenarios where it’s necessary to constantly train the model on new data. This last part is super interesting because it may make it useful for applications on the back end of Google’s search systems, particularly where it is necessary to be able to analyze long sequences of information and understand the relevance from one part near the beginning of the sequence and another part that’s closer to the end.

Other articles focused on the “infinitely long inputs” that this model is capable of but where it’s relevant to SEO is how that ability to handle huge input and “Leave No Context Behind” is what’s relevant to search marketing and how some of Google’s systems might work if Google adapted Infini-attention to their core algorithm.

Read the research paper:

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Featured Image by Shutterstock/JHVEPhoto

Could This Be The Navboost Patent? via @sejournal, @martinibuster

There’s been a lot of speculation of what Navboost is but to my knowledge nobody has pinpointed an adequate patent that could be the original Navboost patent. This patent from 2004 closely aligns with Navboost

So I took the few clues we have about it and identified a couple likely patents.

The clues I was working with are that Google Software Engineer Amit Singhal was involved with Navboost and had a hand in inventing it. Another clue is that Navboost dated to 2005. Lastly, the court documents indicate that Navboost was updated later on so there may be other patents in there about that, which we’ll get to at some point but not in this article.

So I deduced that if Amit Singhal was the inventor then there would be a patent with his name on it and indeed there is, dating from 2004.

Out of all the patents I saw, the two most interesting were these:

• Systems and methods for correlating document topicality and popularity 2004
• Interleaving Search Results 2007

This article will deal with the first one, Systems and methods for correlating document topicality and popularity dating from 2004, which aligns with the known timeline of Navboost dating to 2005.

Patent Does Not Mention Clicks

An interesting quality of this patent is that it doesn’t mention clicks and I suspect that people looking for the Navboost patent may have ignored it because it doesn’t mention clicks.

But the patent discusses concepts related to user interactions and navigational patterns which are references to clicks.

Instances Where User Clicks Are Implied In The Patent

Document Selection and Retrieval:
The patent describes a process where a user selects documents (which can be inferred as clicking on them) from search results. These selections are used to determine the documents’ popularity.

Mapping Documents to Topics:
After documents are selected by users (through clicks), they are mapped to one or more topics. This mapping is a key part of the process, as it associates documents with specific areas of interest or subjects.

User Navigational Patterns:
The patent frequently refers to user navigational patterns, which include how users interact with documents, such as the documents they choose to click on. These patterns are used to compute popularity scores for the documents.

It’s clear that user clicks are a fundamental part of how the patent proposes to assess the popularity of documents.

By analyzing which documents users choose to interact with, the system can assign popularity scores to these documents. These scores, in combination with the topical relevance of the documents, are then used to enhance the accuracy and relevance of search engine results.

Patent: User Interactions Are A Measure Of Popularity

The patent US8595225 makes implicit references to “user clicks” in the context of determining the popularity of documents. Heck, popularity is so important to the patent that it’s in the name of the patent: Systems and methods for correlating document topicality and popularity

User clicks, in this context, refers to the interactions of users with various documents, such as web pages. These interactions are a critical component in establishing the popularity scores for these documents.

The patent describes a method where the popularity of a document is inferred from user navigational patterns, which can only be clicks.

I’d like to stop here and mention that Matt Cutts has discussed in a video that Popularity and PageRank are two different things. Popularity is about what users tend to prefer and PageRank is about authority as evidenced by links.

Matt defined popularity:

“And so popularity in some sense is a measure of where people go whereas PageRank is much more a measure of reputation.”

That definition from about 2014 fits what this patent is talking about in terms of popularity being about where people go.

See Matt Cutts Explains How Google Separates Popularity From True Authority

Watch the YouTube Video: How does Google separate popularity from authority?

How The Patent Uses Popularity Scores

The patent describes multiple ways that it uses popularity scores.

Assigning Popularity Scores:
The patent discusses assigning popularity scores to documents based on user interactions such as the frequency of visits or navigation patterns (Line 1).

Per-Topic Popularity:
It talks about deriving per-topic popularity information by correlating the popularity data associated with each document to specific topics (Line 5).

Popularity Scores in Ranking:
The document describes using popularity scores to order documents among one or more topics associated with each document (Line 13).

Popularity in Document Retrieval:
In the context of document retrieval, the patent outlines using popularity scores for ranking documents (Line 27).

Determining Popularity Based on User Navigation:
The process of determining the popularity score for each document, which may involve using user navigational patterns, is also mentioned (Line 37).

These instances demonstrate the patent’s focus on incorporating the popularity of documents, as determined by user interaction (clicks), into the process of ranking and correlating them to specific topics.

The approach outlined in the patent suggests a more dynamic and user-responsive method of determining the relevance and importance of documents in search engine results.

Navboost Assigns Scores To Documents

I’m going to stop here to also mention that this patent mentions assigning scores to documents, which is how Google executive Eric Lehman described in the trial how Navboost worked:

Speaking about the situation where there wasn’t a lot of click data, Lehman testified:

“And so I think Navboost does kind of the natural thing, which is, in the face of that kind of uncertainty, you take gentler measures. So you might modify the score of a document but more mildly than if you had more data.”

That’s another connection to Navboost in that the trial description and the patent describe using User Interaction for scoring webpages.

The more this patent is analyzed, the more it looks like what the trial documents described as Navboost.

Read the patent here:

Systems and methods for correlating document topicality and popularity

Featured Image by Shutterstock/Sabelskaya