Related papers: Explainable and Discourse Topic-aware Neural Langu…

Language models trained on billions of tokens have recently led to unprecedented results on many NLP tasks. This success raises the question of whether, in principle, a system can ever ``understand'' raw text without access to some form of…

This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discover word clusters indicating what a conversation concerns…

The abundant sequential documents such as online archival, social media and news feeds are streamingly updated, where each chunk of documents is incorporated with smoothly evolving yet dependent topics. Such digital texts have attracted…

We propose a large language model explainability technique for obtaining faithful natural language explanations by grounding the explanations in a reasoning process. When converted to a sequence of tokens, the outputs of the reasoning…

Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing aligned latent topics. However, most existing methods suffer from producing repetitive topics that hinder further analysis and performance decline…

Topic modeling has found wide application in many problems where latent structures of the data are crucial for typical inference tasks. When applying a topic model, a relatively standard pre-processing step is to first build a vocabulary of…

A huge volume of user-generated content is daily produced on social media. To facilitate automatic language understanding, we study keyphrase prediction, distilling salient information from massive posts. While most existing methods extract…

The training of topic models for a multilingual environment is a challenging task, requiring the use of sophisticated algorithms, topic-aligned corpora, and manual evaluation. These difficulties are further exacerbated when the developer…

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to…

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…

Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified given observable moments of a certain order. We consider…

Traditional Relational Topic Models provide a way to discover the hidden topics from a document network. Many theoretical and practical tasks, such as dimensional reduction, document clustering, link prediction, benefit from this revealed…

In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a…

Researchers have relegated natural language processing tasks to Transformer-type models, particularly generative models, because these models exhibit high versatility when performing generation and classification tasks. As the size of these…

By illuminating latent structures in a corpus of text, topic models are an essential tool for categorizing, summarizing, and exploring large collections of documents. Probabilistic topic models, such as latent Dirichlet allocation (LDA),…

Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in…

Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…

In the era of digitalization, as individuals increasingly rely on digital platforms for communication and news consumption, various actors employ linguistic strategies to influence public perception. While models have become proficient at…

Topic modeling aims to produce interpretable topic representations and topic--document correspondences from corpora, but classical neural topic models (NTMs) remain constrained by limited representation assumptions and semantic abstraction…

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers…