English
Related papers

Related papers: Probabilistic Topic Modelling with Transformer Rep…

200 papers

Generating interpretable visualizations from complex data is a common problem in many applications. Two key ingredients for tackling this issue are clustering and representation learning. However, current methods do not yet successfully…

Machine Learning · Computer Science 2020-06-11 Laura Manduchi , Matthias Hüser , Julia Vogt , Gunnar Rätsch , Vincent Fortuin

Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that characterizes a document. Prior work has found that internal…

Computation and Language · Computer Science 2023-12-25 Liyi Zhang , R. Thomas McCoy , Theodore R. Sumers , Jian-Qiao Zhu , Thomas L. Griffiths

Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…

Computation and Language · Computer Science 2026-05-07 Minjie Qiang , Mingming Zhang , Xiaoyi Bao , Xing Fu , Yu Cheng , Weiqiang Wang , Zhongqing Wang , Ningtao Wang

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure…

Information Retrieval · Computer Science 2019-12-10 Feng Nan , Ran Ding , Ramesh Nallapati , Bing Xiang

Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does…

Computation and Language · Computer Science 2018-05-23 Yishu Miao , Edward Grefenstette , Phil Blunsom

Thematic investing, which aims to construct portfolios aligned with structural trends, remains a challenging endeavor due to overlapping sector boundaries and evolving market dynamics. A promising direction is to build semantic…

Portfolio Management · Quantitative Finance 2025-09-01 Hoyoung Lee , Wonbin Ahn , Suhwan Park , Jaehoon Lee , Minjae Kim , Sungdong Yoo , Taeyoon Lim , Woohyung Lim , Yongjae Lee

Probabilistic graphical models (PGMs) are widely used to discover latent structure in data, but their success hinges on selecting an appropriate model design. In practice, model specification is difficult and often requires iterative…

Machine Learning · Computer Science 2026-04-08 Kevin Zhang , Yixin Wang

In this paper we present a modification to a latent topic model, which makes the model exploit supervision to produce a factorized representation of the observed data. The structured parameterization separately encodes variance that is…

Machine Learning · Computer Science 2013-04-24 Cheng Zhang , Carl Henrik Ek , Andreas Damianou , Hedvig Kjellstrom

Topic-controllable summarization is an emerging research area with a wide range of potential applications. However, existing approaches suffer from significant limitations. For example, the majority of existing methods built upon recurrent…

Computation and Language · Computer Science 2024-04-18 Tatiana Passali , Grigorios Tsoumakas

Majority of the text modelling techniques yield only point-estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We…

Computation and Language · Computer Science 2020-08-03 Santosh Kesiraju , Oldřich Plchot , Lukáš Burget , Suryakanth V Gangashetty

A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation. For instance, visual object recognition involves…

Machine Learning · Statistics 2015-04-03 Ankit B. Patel , Tan Nguyen , Richard G. Baraniuk

Word embedding is central to neural machine translation (NMT), which has attracted intensive research interest in recent years. In NMT, the source embedding plays the role of the entrance while the target embedding acts as the terminal.…

Computation and Language · Computer Science 2019-06-10 Xuebo Liu , Derek F. Wong , Yang Liu , Lidia S. Chao , Tong Xiao , Jingbo Zhu

Efficient probability density estimation is a core challenge in statistical machine learning. Tensor-based probabilistic graph methods address interpretability and stability concerns encountered in neural network approaches. However, a…

Machine Learning · Computer Science 2023-12-14 Ruituo Wu , Jiani Liu , Ce Zhu , Anh-Huy Phan , Ivan V. Oseledets , Yipeng Liu

We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence. We argue that this…

Computation and Language · Computer Science 2017-08-03 Ramesh Nallapati , Igor Melnyk , Abhishek Kumar , Bowen Zhou

Topic models are widely used for thematic structure discovery in text. But traditional topic models often require dedicated inference procedures for specific tasks at hand. Also, they are not designed to generate word-level semantic…

Artificial Intelligence · Computer Science 2019-08-22 Rui Wang , Deyu Zhou , Yulan He

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post

Production of news content is growing at an astonishing rate. To help manage and monitor the sheer amount of text, there is an increasing need to develop efficient methods that can provide insights into emerging content areas, and stratify…

Computation and Language · Computer Science 2020-10-29 M. Tarik Altuncu , Sophia N. Yaliraki , Mauricio Barahona

The time at which a message is communicated is a vital piece of metadata in many real-world natural language processing tasks such as Topic Detection and Tracking (TDT). TDT systems aim to cluster a corpus of news articles by event, and in…

Computation and Language · Computer Science 2024-03-27 Hang Jiang , Doug Beeferman , Weiquan Mao , Deb Roy

Topic models are a popular tool for clustering and analyzing textual data. They allow texts to be classified on the basis of their affiliation to the previously calculated topics. Despite their widespread use in research and application, an…

Artificial Intelligence · Computer Science 2024-03-07 Johannes Hirth , Tom Hanika

Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been…

Machine Learning · Statistics 2018-10-25 Dallas Card , Chenhao Tan , Noah A. Smith