English
Related papers

Related papers: Learning Topics using Semantic Locality

200 papers

Traditionally, Latent Dirichlet Allocation (LDA) ingests words in a collection of documents to discover their latent topics using word-document co-occurrences. However, it is unclear how to achieve the best results for languages without…

Computation and Language · Computer Science 2021-08-25 Jin Cheevaprawatdomrong , Alexandra Schofield , Attapol T. Rutherford

The advent of NMT has expanded the scope of translation beyond isolated sentences, enabling context to be preserved across paragraphs and documents. However, current evaluation metrics largely remain restricted to the sentence level and…

Computational Engineering, Finance, and Science · Computer Science 2026-04-23 Hyeokmin Lee , Youngkyu Kim , Byounghyun Yoo

Stopword removal is a critical stage in many Machine Learning methods but often receives little consideration, it interferes with the model visualizations and disrupts user confidence. Inappropriately chosen or hastily omitted stopwords not…

Human-Computer Interaction · Computer Science 2025-01-20 Shuangjiang Xue , Pierre Le Bras , David A. Robb , Mike J. Chantler , Stefano Padilla

The growing use of unstructured text in business research makes topic modeling a central tool for constructing explanatory variables from reviews, social media, and open-ended survey responses, yet existing approaches function poorly as…

Computation and Language · Computer Science 2026-03-05 Stephan Ludwig , Peter J. Danaher , Xiaohao Yang

Word Sense Disambiguation is an open problem in Natural Language Processing which is particularly challenging and useful in the unsupervised setting where all the words in any given text need to be disambiguated without using any labeled…

Computation and Language · Computer Science 2018-01-09 Devendra Singh Chaplot , Ruslan Salakhutdinov

We propose a geometric algorithm for topic learning and inference that is built on the convex geometry of topics arising from the Latent Dirichlet Allocation (LDA) model and its nonparametric extensions. To this end we study the…

Machine Learning · Statistics 2016-10-31 Mikhail Yurochkin , XuanLong Nguyen

Exponential growth of the web increased the importance of web document classification and data mining. To get the exact information, in the form of knowing what classes a web document belongs to, is expensive. Automatic classification of…

Information Retrieval · Computer Science 2014-06-24 R. K. Roul , S. K. Sahay

This paper introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Zhongwei Xie , Ling Liu , Yanzhao Wu , Luo Zhong , Lin Li

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Computation and Language · Computer Science 2020-02-28 Duygu Ataman , Wilker Aziz , Alexandra Birch

Keyphrases are useful for a variety of purposes, including summarizing, indexing, labeling, categorizing, clustering, highlighting, browsing, and searching. The task of automatic keyphrase extraction is to select keyphrases from within the…

Machine Learning · Computer Science 2007-05-23 Peter D. Turney

Specificity is important for extracting collocations, keyphrases, multi-word and index terms [Newman et al. 2012]. It is also useful for tagging, ontology construction [Ryu and Choi 2006], and automatic summarization of documents [Louis and…

Computation and Language · Computer Science 2014-03-11 Michael Stewart

Dynamic topic models (DTMs) are very effective in discovering topics and capturing their evolution trends in time series data. To do posterior inference of DTMs, existing methods are all batch algorithms that scan the full dataset before…

Machine Learning · Statistics 2016-02-22 Arnab Bhadury , Jianfei Chen , Jun Zhu , Shixia Liu

Probabilistic topic models are a powerful tool for extracting latent themes from large text datasets. In many text datasets, we also observe per-document covariates (e.g., source, style, political affiliation) that act as environments that…

Computation and Language · Computer Science 2024-11-04 Dominic Sobhani , Amir Feder , David Blei

Many real systems have been modelled in terms of network concepts, and written texts are a particular example of information networks. In recent years, the use of network methods to analyze language has allowed the discovery of several…

Computation and Language · Computer Science 2016-06-28 Henrique F. de Arruda , Luciano da F. Costa , Diego R. Amancio

The present study proposes a novel method of trend detection and visualization - more specifically, modeling the change in a topic over time. Where current models used for the identification and visualization of trends only convey the…

Computation and Language · Computer Science 2023-09-19 Angad Sandhu , Aneesh Edara , Vishesh Narayan , Faizan Wajid , Ashok Agrawala

In this project we propose a new approach for emotion recognition using web-based similarity (e.g. confidence, PMI and PMING). We aim to extract basic emotions from short sentences with emotional content (e.g. news titles, tweets,…

Computation and Language · Computer Science 2017-01-12 Valentina Franzoni , Giulio Biondi , Alfredo Milani , Yuanxi Li

Recent advances in pre-trained language modeling have facilitated significant progress across various natural language processing (NLP) tasks. Word masking during model training constitutes a pivotal component of language modeling in…

Computation and Language · Computer Science 2024-02-27 Anas Belfathi , Ygor Gallina , Nicolas Hernandez , Richard Dufour , Laura Monceaux

Over the years, topic models have provided an efficient way of extracting insights from text. However, while many models have been proposed, none are able to model topic temporality and hierarchy jointly. Modelling time provide more precise…

Information Retrieval · Computer Science 2023-01-25 Judicael Poumay , Ashwin Ittoo

Search engines perform the task of retrieving information related to the user-supplied query words. This task has two parts; one is finding "featured words" which describe an article best and the other is finding a match among these words…

Neural and Evolutionary Computing · Computer Science 2007-05-23 A. Das , M. Marko , A. Probst , M. A. Porter , C. Gershenson

Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple…

Computation and Language · Computer Science 2018-02-14 Marzieh Fadaee , Arianna Bisazza , Christof Monz