Amr Ahmed

Google Inc. | Google · Research Department

Opinion summarization is the task of creating summaries capturing popular opinions from user reviews. In this paper, we introduce Geodesic Summarizer (GeoSumm), a novel system to perform unsupervised extractive opinion summarization. GeoSumm involves an encoder-decoder based representation learning model, that generates representations of text as a...

High-quality dialogue-summary paired data is expensive to produce and domain-sensitive, making abstractive dialogue summarization a challenging task. In this work, we propose the first unsupervised abstractive dialogue summarization model for tete-a-tetes (SuTaT). Unlike standard text summarization, a dialogue summarization method should consider t...

Hierarchical clustering is a critical task in numerous domains. Many approaches are based on heuristics and the properties of the resulting clusterings are studied post hoc. However, in several applications, there is a natural cost function that can be used to characterize the quality of the clustering. In those cases, hierarchical clustering can b...

Bottom-up algorithms such as the classic hierarchical agglomerative clustering, are highly effective for hierarchical as well as flat clustering. However, the large number of rounds and their sequential nature limit the scalability of agglomerative clustering. In this paper, we present an alternative round-based bottom-up hierarchical clustering, t...

High-quality dialogue-summary paired data is expensive to produce and domain-sensitive, making abstractive dialogue summarization a challenging task. In this work, we propose the first unsupervised abstractive dialogue summarization model for tete-a-tetes (SuTaT). Unlike standard text summarization, a dialogue summarization method should consider t...

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces...

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-st...

A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. The primary goal of the agent is to identify the latent state, after which it can act optimally. This setting is a natural midpoint between online and offline learning---complex models can be learned offline...

Learning continuous representations of discrete objects such as text, users, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often ignore the underlying structures (e.g. natural groupings and similarities) and embed the objects independently into indiv...

Hierarchical clustering is typically performed using algorithmic-based optimization searching over the discrete space of trees. While these optimization methods are often effective, their discreteness restricts them from many of the benefits of their continuous counterparts, such as scalable stochastic optimization and the joint optimization of mul...

Long Short-Term Memory (LSTM) is one of the most powerful sequence models for user browsing history \citetan2016improved,korpusik2016recurrent or natural language text \citemikolov2010recurrent.Despite the strong performance, it has not gained popularity for user-facing applications, mainly owing to a large number of parameters and lack of interpre...

Long Short-Term Memory (LSTM) is one of the most powerful sequence models. Despite the strong performance, however, it lacks the nice interpretability as in state space models. In this paper, we present a way to combine the best of both worlds by introducing State Space LSTM (SSL) models that generalizes the earlier work \cite{zaheer2017latent} of...

Topic models are often applied in industrial settings to discover user profiles from activity logs where documents correspond to users and words to complex objects such as web sites and installed apps. Standard topic models ignore the content-based similarity structure between these objects largely because of the inability of the Dirichlet prior to...

The problem of recommending items to users is of high practical importance. For instance, many web services try to find relevant recommendations for the users, e.g., finding relevant movies, social-media friends, restaurants, shopping items, etc. The expansion of the Web and the ever-growing number of people who use web services render the problem...

In online shopping, users usually express their intent through search queries. However, these queries are often ambiguous. For example, it is more likely (and easier) for users to write a query like "high-end bike" than "21 speed carbon frames jamis or giant road bike". It is challenging to interpret these ambiguous queries and thus search result a...

Recommender systems traditionally assume that user profiles and movie attributes are static. Temporal dynamics are purely reactive, that is, they are inferred after they are observed, e.g. after a user's taste has changed or based on hand-engineered temporal bias corrections for movies. We propose Recurrent Recommender Networks (RRN) that are able...

Understanding a user's motivations provides valuable information beyond the ability to recommend items. Quite often this can be accomplished by perusing both ratings and review texts. Unfortunately matrix factorization approaches to recommendation result in large, complex models that are difficult to interpret. In this paper, we attack this problem...

Understanding a user's motivations provides valuable information beyond the ability to recommend items. Quite often this can be accomplished by perusing both ratings and review texts, since it is the latter where the reasoning for specific preferences is explicitly expressed. Unfortunately matrix factorization approaches to recommendation result in...

Latent variable models have accumulated a considerable amount of interest from the industry and academia for their versatility in a wide range of applications. A large amount of effort has been made to develop systems that is able to extend the systems to a large scale, in the hope to make use of them on industry scale data. In this paper, we descr...

Business-to-consumer (B2C) emails are usually generated by filling structured user data (e.g.purchase, event) into templates. Extracting structured data from B2C emails allows users to track important information on various devices. However, it also poses several challenges, due to the requirement of short response time for massive data volume, the...

Clusters in document streams, such as online news articles, can be induced by their textual contents, as well as by the temporal dynamics of their arriving patterns. Can we leverage both sources of information to obtain a better clustering of the documents, and distill information that is not possible to extract using contents only? In this paper,...

Matrix completion and approximation are popular tools to capture a user's preferences for recommendation and to approximate missing data. Instead of using low-rank factorization we take a drastically different approach, based on the simple insight that an additive model of co-clusterings allows one to approximate matrices efficiently. This allows u...

Inferring movement trajectories can be a challenging task, in particular when detailed tracking information is not available due to privacy and data collection constraints. In this paper we present a complete and computationally tractable model for estimating and predicting trajectories based on sparsely sampled, anonymous GPS land-marks that we ca...

Matrix completion and approximation are popular tools to capture a user's preferences for recommendation and to approximate missing data. Instead of using low-rank factorization we take a drastically different approach, based on the simple insight that an additive model of co-clusterings allows one to approximate matrices efficiently. This allows u...

Inference in topic models typically involves a sampling step to associate latent variables with observations. Unfortunately the generative model loses sparsity as the amount of data increases, requiring O(k) operations per word for k topics. In this paper we propose an algorithm which scales linearly with the number of actually instantiated topics...

Personalized recommender systems based on latent factor models are widely used to increase sales in e-commerce. Such systems use the past behavior of users to recommend new items that are likely to be of interest to them. However, latent factor model suffer from sparse user-item interaction in online shopping data: for a large portion of items that...

Many estimation tasks come in groups and hierarchies of related problems. In this paper we propose a hierarchical model and a scalable algorithm to perform inference for multitask learning. It infers task correlation and subtask structure in a joint sparse setting. Implementation is achieved by a distributed subgradient oracle and the successive ap...

Large amounts of data arise in a multitude of situations, ranging from bioinformatics to astronomy, manufacturing, and medical applications. For concreteness our tutorial focuses on data obtained in the context of the internet, such as user generated content (microblogs, e-mails, messages), behavioral data (locations, interactions, clicks, queries)...

Online content have become an important medium to disseminate information and express opinions. With their proliferation, users are faced with the problem of missing the big picture in a sea of irrelevant and/or diverse content. In this paper, we addresses the problem of information organization of online document collections, and provide algorithm...

Natural graphs, such as social networks, email graphs, or instant messaging patterns, have become pervasive through the internet. These graphs are massive, often containing hundreds of millions of nodes and billions of edges. While some theoretical models have been proposed to study such graphs, their analysis is still difficult due to the scale an...

As search pages are becoming increasingly complex, with images and nonlinear page layouts, understanding how users examine the page is important. We present a lab study on the effect of a rich informational panel to the right of the search result column, on eye and mouse behavior. Using eye and mouse data, we show that the flow of user attention on...

With the availability of cheap location sensors, geotagging of messages in online social networks is proliferating. For instance, Twitter, Facebook, Foursquare, and Google+ provide these services both explicitly by letting users choose their location or implicitly via a sensor. This paper presents an integrated generative model of location and mess...

Audience selection is a key problem in display advertising systems in which we need to select a list of users who are interested (i.e., most likely to buy) in an advertising campaign. The users' past feedback on this campaign can be leveraged to construct such a list using collaborative filtering techniques such as matrix factorization. However, th...

Items in recommender systems are usually associated with annotated attributes: for e.g., brand and price for products; agency for news articles, etc. Such attributes are highly informative and must be exploited for accurate recommendation. While learning a user preference model over these attributes can result in an interpretable recommender system...

Much natural data is hierarchical in nature. Moreover, this hierarchy is often shared between different instances. We introduce the nested Chinese Restaurant Franchise Process to obtain both hierarchical tree-structured representations for objects, akin to (but more general than) the nested Chinese Restaurant Process while sharing their structure a...

A typical behavioral targeting system optimizing purchase activities, called conversions, faces two main challenges: the web-scale amounts of user histories to process on a daily ba- sis, and the relative sparsity of conversions. In this paper, we try to address these challenges through feature selec- tion. We formulate a multi-task (or group) feat...

Since 2000, Baidu has set its mission as providing the best way for people to find what they're looking for. Today, the company has become the world's largest Chinese search engine. Everyday, we process billions of search queries and serve hundreds of ...

A supervised topic model can use side information such as ratings or labels associated with documents or images to discover more predictive low dimensional topical representations of the data. However, existing supervised topic models predominantly employ likelihood-driven objective functions for learning and inference, leaving the popular and pote...

Recommender systems based on latent factor models have been effectively used for understanding user interests and predicting future actions. Such models work by projecting the users and items into a smaller dimensional space, thereby clustering similar users and items together and subsequently compute similarity between unknown user-item pairs. Whe...

Relevance, diversity and personalization are key issues when presenting content which is apt to pique a user's interest. This is particularly true when presenting an engaging set of news stories. In this paper we propose an efficient algorithm for selecting a small subset of relevant articles from a streaming news corpus. It offers three key pieces...

Micro-blogging services have become indispensable communication tools for online users for disseminating breaking news, eyewitness accounts, individual expression, and protest groups. Recently, Twitter, along with other online social networking services such as Foursquare, Gowalla, Facebook and Yelp, have started supporting location services in the...

Topic models have proven to be a useful tool for discovering latent structures in document collections. However, most document collections often come as temporal streams and thus several aspects of the latent structure such as the number of topics, the topics' distribution and popularity are time-evolving. Several models exist that model the evolut...

Latent variable techniques are pivotal in tasks ranging from predicting user click patterns and targeting ads to organizing the news and managing user generated content. Latent variable techniques like topic modeling, clustering, and subspace estimation provide substantial insight into the latent structure of complex data with little or no external...

We describe �ã Hokusai, a real time system which is able to capture frequency information for streams of arbitrary sequences of symbols. The algorithm uses the Count-Min sketch as its basis and exploits the fact that sketching is linear. It provides real time statistics of arbitrary events, e.g. streams of queries as a function of time. We use a fa...

Scalable data analysis has come a long way since the intro- duction of the MapReduce paradigm a decade ago. In this tutorial we present algorithms for synchronous and asyn- chronous data processing. They are are capable of dealing with the amounts of data typically available on the internet. We given a brief description of the problems one faces wh...

Clustering is a key component in any data analysis toolbox. Despite its importance, scalable algorithms often eschew rich statistical models in favor of simpler descriptions such as k-means clustering. In this paper we present a sampler, capable of estimating mixtures of exponential families. At its heart lies a novel proposal distribution using ra...

Historical user activity is key for building user profiles to predict the user behavior and affinities in many web applications such as targeting of online advertising, content personalization and social recommendations. User profiles are temporal, and changes in a user's activity patterns are particularly useful for improved prediction and recomme...

News clustering, categorization and analysis are key components of any news portal. They require algorithms capable of dealing with dynamic data to cluster, interpret and to temporally aggregate news articles. These three tasks are often solved separately. In this paper we present a unified framework to group incoming news articles into temporary b...

We present the time-dependent topic-cluster model, a hierarchical approach for combining Latent Dirichlet Allocation and clustering via the Recurrent Chinese Restaurant Process. It inherits the advantages of both of its constituents, namely interpretability and concise representation. We show how it can be applied to streaming collections of object...

Graphical models are an effective tool for analyzing structured and relational data. In particular, they allow us to arrive at insights that are implicit, i.e. latent in the data. Dealing with such data on the internet poses a range of challenges. Firstly, the sheer size renders many well-known inference algorithms infeasible. Secondly, the problem...

Generative models of text typically associate a multinomial with every class label or topic. Even in simple models this requires the estimation of thousands of parameters; in multifaceted latent variable models, standard approaches require additional latent "switching" variables for every token, complicating inference. In this paper, we propose an...

In this tutorial we give an overview over applications and scalable inference in graphical models for the internet. Structured data analysis has become a key enabling technique to process significant amounts of data, ranging from entity extraction on webpages to sentiment and topic analysis for news articles and comments. Our tutorial covers large...

Online content have become an important medium to disseminate information and express opinions. With the proliferation of online document collections, users are faced with the problem of missing the big picture in a sea of irrelevant and/or diverse content. In this thesis, we addresses the problem of information organization of online document coll...

With the proliferation of user-generated articles over the web, it becomes imperative to develop automated methods that are aware of the ideological-bias implicit in a document collection. While there exist methods that can classify the ideological bias of a given document, little has been done toward understanding the nature of this bias on a topi...

The SLIF project combines text-mining and image processing to extract structured information from biomedical literature.SLIF extracts images and their captions from published papers. The captions are automatically parsed for relevant biological entities (protein and cell type names), while the images are classified according to their type (e.g., mi...

Slif uses a combination of text-mining and image processing to extract information from figures in the biomedical literature. It also uses innovative extensions to traditional latent topic modeling to provide new ways to traverse the literature. Slif provides a publicly available searchable database (http://slif.cbi.cmu.edu). Slif originally focuse...

Supervised topic models utilize document's side information for discovering predictive low dimensional representations of documents. Existing models apply the likelihood-based estimation. In this paper, we present a general framework of max-margin supervised topic models for both continuous and categorical response variables. Our approach, the maxi...

A plausible representation of the relational information among entities in dynamic systems such as a living cell or a social community is a stochastic network that is topologically rewiring and semantically evolving over time. Although there is a rich literature in modeling static or temporally invariant networks, little has been done toward recove...

Due to the dynamic nature of biological systems, biological networks underlying temporal process such as the development of {\it Drosophila melanogaster} can exhibit significant topological changes to facilitate dynamic regulatory functions. Thus it is essential to develop methodologies that capture the temporal evolution of networks, which make it...

Supervised topic models utilize document's side information for discovering predictive low dimensional representations of docu- ments; and existing models apply likelihood- based estimation. In this paper, we present a max-margin supervised topic model for both continuous and categorical response variables. Our approach, the maximum en- tropy discr...

A major source of information (often the most crucial and informa- tive part) in scholarly articles from scientific journals, proceedings and books are the figures that directly provide images and other graphical illustrations of key experimental results and other scien- tific contents. In biological articles, a typical figure often comprises multi...

Stochastic networks are a plausible representation of the relational information among entities in dynamic systems such as living cells or social communities. While there is a rich literature in estimating a static or temporally invariant network from observation data, little has been done toward estimating time-varying networks from time series of...

Building visual recognition models that adapt across different do- mains is a challenging task for computer vision. While feature-learning machines in the form of hierarchial feed-forward models (e.g., convolutional neural net- works) showed promise in this direction, they are still difficult to train especially when few training examples are avail...

In this work, we address the problem of joint modeling of text and citations in the topic modeling framework. We present two different models called the Pairwise-Link-LDA and the Link-PLSA-LDA models. The Pairwise-Link-LDA model combines the ideas of LDA [4] and Mixed Membership Block Stochastic Models [1] and allows modeling arbitrary link structu...

In many problems arising in biology, social sciences and various other fields, it is often necessary to analyze populations of entities such as molecules or individuals that are interconnected by a set of relationships. Studying networks of these kinds can reveal a wide range of information. While there is a rich literature on modeling static netwo...

Clustering is an important data mining task for exploration and visualization of difierent data types like news stories, scientiflc publications, weblogs, etc. Due to the evolving nature of these data, evolutionary clustering, also known as dynamic clustering, has recently emerged to cope with the challenges of mining temporally smooth clusters ove...

Statistical topic models such as the Latent Dirichlet Al- location (LDA) have emerged as an attractive framework to model, visualize and summarize large document collections in a completely unsupervised fashion. One of the limitations of this family of models is their assumption of exchangeabil- ity of words within documents, which results in a `ba...

The Logistic-Normal Topic Admixture Model (LoNTAM), also known as correlated topic model (Blei and Lafierty, 2005), is a promis- ing and expressive admixture-based text model. It can capture topic correlations via the use of a logistic-normal distribu- tion to model non-trivial variabilities in the topic mixing vectors underlying documents. However...

In the dynamic distributed task assignment (DDTA) problem, a team of agents is required to accomplish a set of tasks while maximizing the overall team utility. An effective solution to this problem needs to address two closely related questions: first, how to find a near-optimal assignment from agents to tasks under resource constraints, and second...

1. The Temporal Dirichlet Process Mixture Model Dirichlet process mixture models provide a flexible Bayesian framework for estimating a distribution as an infinite mixture of simpler distributions that could identify latent classes in the data [1]. However the full exchangeability assumption they employ makes them an unappealing choice for modeling...

Abstract Aplausible representation of the relational information among,entities in dynamic,systems such as a living cell or a social community,is a stochastic network which is topologicallyrewiring and semantically evolving over time. While there is a rich literature on modeling static or temporally invariant networks, until recently, little has be...