Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Variational Inference In Pachinko Allocation Machines

Apr 21, 2018
Akash Srivastava, Charles Sutton

The Pachinko Allocation Machine (PAM) is a deep topic model that allows representing rich correlation structures among topics by a directed acyclic graph over topics. Because of the flexibility of the model, however, approximate inference is very difficult. Perhaps for this reason, only a small number of potential PAM architectures have been explored in the literature. In this paper we present an efficient and flexible amortized variational inference method for PAM, using a deep inference network to parameterize the approximate posterior distribution in a manner similar to the variational autoencoder. Our inference method produces more coherent topics than state-of-art inference methods for PAM while being an order of magnitude faster, which allows exploration of a wider range of PAM architectures than have previously been studied.


  Access Paper or Ask Questions

An Exploratory Study of (#)Exercise in the Twittersphere

Dec 08, 2018
George Shaw, Amir Karami

Social media analytics allows us to extract, analyze, and establish semantic from user-generated contents in social media platforms. This study utilized a mixed method including a three-step process of data collection, topic modeling, and data annotation for recognizing exercise related patterns. Based on the findings, 86% of the detected topics were identified as meaningful topics after conducting the data annotation process. The most discussed exercise-related topics were physical activity (18.7%), lifestyle behaviors (6.6%), and dieting (4%). The results from our experiment indicate that the exploratory data analysis is a practical approach to summarizing the various characteristics of text data for different health and medical applications.


  Access Paper or Ask Questions

Content Modeling Using Latent Permutations

Jan 15, 2014
Harr Chen, S. R. K. Branavan, Regina Barzilay, David R. Karger

We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organization of document topics. We propose a global model in which both topic selection and ordering are biased to be similar across a collection of related documents. We show that this space of orderings can be effectively represented using a distribution over permutations called the Generalized Mallows Model. We apply our method to three complementary discourse-level tasks: cross-document alignment, document segmentation, and information ordering. Our experiments show that incorporating our permutation-based model in these applications yields substantial improvements in performance over previously proposed methods.

* Journal Of Artificial Intelligence Research, Volume 36, pages 129-163, 2009 

  Access Paper or Ask Questions

Analysis of Risk Factor Domains in Psychosis Patient Health Records

Sep 15, 2018
Eben Holderness, Nicholas Miller, Philip Cawkwell, Kirsten Bolton, James Pustejovsky, Marie Meteer, Mei-Hua Hall

Readmission after discharge from a hospital is disruptive and costly, regardless of the reason. However, it can be particularly problematic for psychiatric patients, so predicting which patients may be readmitted is critically important but also very difficult. Clinical narratives in psychiatric electronic health records (EHRs) span a wide range of topics and vocabulary; therefore, a psychiatric readmission prediction model must begin with a robust and interpretable topic extraction component. We created a data pipeline for using document vector similarity metrics to perform topic extraction on psychiatric EHR data in service of our long-term goal of creating a readmission risk classifier. We show initial results for our topic extraction model and identify additional features we will be incorporating in the future.

* Accepted at EMNLP-LOUHI 2018 

  Access Paper or Ask Questions

A Dataset of General-Purpose Rebuttal

Sep 01, 2019
Matan Orbach, Yonatan Bilu, Ariel Gera, Yoav Kantor, Lena Dankin, Tamar Lavee, Lili Kotlerman, Shachar Mirkin, Michal Jacovi, Ranit Aharonov, Noam Slonim

In Natural Language Understanding, the task of response generation is usually focused on responses to short texts, such as tweets or a turn in a dialog. Here we present a novel task of producing a critical response to a long argumentative text, and suggest a method based on general rebuttal arguments to address it. We do this in the context of the recently-suggested task of listening comprehension over argumentative content: given a speech on some specified topic, and a list of relevant arguments, the goal is to determine which of the arguments appear in the speech. The general rebuttals we describe here (written in English) overcome the need for topic-specific arguments to be provided, by proving to be applicable for a large set of topics. This allows creating responses beyond the scope of topics for which specific arguments are available. All data collected during this work is freely available for research.

* EMNLP 2019 

  Access Paper or Ask Questions

Visualization of Clandestine Labs from Seizure Reports: Thematic Mapping and Data Mining Research Directions

Mar 05, 2015
William Hsu, Mohammed Abduljabbar, Ryuichi Osuga, Max Lu, Wesam Elshamy

The problem of spatiotemporal event visualization based on reports entails subtasks ranging from named entity recognition to relationship extraction and mapping of events. We present an approach to event extraction that is driven by data mining and visualization goals, particularly thematic mapping and trend analysis. This paper focuses on bridging the information extraction and visualization tasks and investigates topic modeling approaches. We develop a static, finite topic model and examine the potential benefits and feasibility of extending this to dynamic topic modeling with a large number of topics and continuous time. We describe an experimental test bed for event mapping that uses this end-to-end information retrieval system, and report preliminary results on a geoinformatics problem: tracking of methamphetamine lab seizure events across time and space.

* In Proceedings of The 2nd European Workshop on Human-Computer Interaction and Information Retrieval EuroHCIR2012, pages 43--46, Nijmegen, the Netherlands, 24th/25th August 2012 

  Access Paper or Ask Questions

ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Tasks

Mar 05, 2018
Kavita Ganesan

Evaluation of summarization tasks is extremely crucial to determining the quality of machine generated summaries. Over the last decade, ROUGE has become the standard automatic evaluation measure for evaluating summarization tasks. While ROUGE has been shown to be effective in capturing n-gram overlap between system and human composed summaries, there are several limitations with the existing ROUGE measures in terms of capturing synonymous concepts and coverage of topics. Thus, often times ROUGE scores do not reflect the true quality of summaries and prevents multi-faceted evaluation of summaries (i.e. by topics, by overall content coverage and etc). In this paper, we introduce ROUGE 2.0, which has several updated measures of ROUGE: ROUGE-N+Synonyms, ROUGE-Topic, ROUGE-Topic+Synonyms, ROUGE-TopicUniq and ROUGE-TopicUniq+Synonyms; all of which are improvements over the core ROUGE measures.


  Access Paper or Ask Questions

A Nested HDP for Hierarchical Topic Models

Jan 16, 2013
John Paisley, Chong Wang, David Blei, Michael I. Jordan

We develop a nested hierarchical Dirichlet process (nHDP) for hierarchical topic modeling. The nHDP is a generalization of the nested Chinese restaurant process (nCRP) that allows each word to follow its own path to a topic node according to a document-specific distribution on a shared tree. This alleviates the rigid, single-path formulation of the nCRP, allowing a document to more easily express thematic borrowings as a random effect. We demonstrate our algorithm on 1.8 million documents from The New York Times.

* Submitted to the workshop track of the International Conference on Learning Representations 2013. It is a short version of a longer paper 

  Access Paper or Ask Questions

Enriching WordNet concepts with topic signatures

Sep 19, 2001
Eneko Agirre, Olatz Ansa, Eduard Hovy, David Martinez

This paper explores the possibility of enriching the content of existing ontologies. The overall goal is to overcome the lack of topical links among concepts in WordNet. Each concept is to be associated to a topic signature, i.e., a set of related words with associated weights. The signatures can be automatically constructed from the WWW or from sense-tagged corpora. Both approaches are compared and evaluated on a word sense disambiguation task. The results show that it is possible to construct clean signatures from the WWW using some filtering techniques.

* Proceedings of the NAACL workshop on WordNet and Other lexical Resources: Applications, Extensions and Customizations. Pittsburg, 2001 
* Author list corrected 

  Access Paper or Ask Questions

User Ex Machina : Simulation as a Design Probe in Human-in-the-Loop Text Analytics

Jan 06, 2021
Anamaria Crisan, Michael Correll

Topic models are widely used analysis techniques for clustering documents and surfacing thematic elements of text corpora. These models remain challenging to optimize and often require a "human-in-the-loop" approach where domain experts use their knowledge to steer and adjust. However, the fragility, incompleteness, and opacity of these models means even minor changes could induce large and potentially undesirable changes in resulting model. In this paper we conduct a simulation-based analysis of human-centered interactions with topic models, with the objective of measuring the sensitivity of topic models to common classes of user actions. We find that user interactions have impacts that differ in magnitude but often negatively affect the quality of the resulting modelling in a way that can be difficult for the user to evaluate. We suggest the incorporation of sensitivity and "multiverse" analyses to topic model interfaces to surface and overcome these deficiencies.

* 16 Pages, 9 Figures, CHI 2021 Conference 

  Access Paper or Ask Questions

<<
63
64
65
66
67
68
69
70
71
72
73
74
75
>>