相关论文: Tethering Broken Themes: Aligning Neural Topic Mod…

Detecting and tracking emerging trends and weak signals in large, evolving text corpora is vital for applications such as monitoring scientific literature, managing brand reputation, surveilling critical infrastructure and more generally to…

Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching…

Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations…

Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise. Standard practice aggregates labels via majority vote or simple…

Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model…

Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of learn-to-compare. The goal of this approach is to add robustness to deep learning…

Topic discovery in scientific literature provides valuable insights for researchers to identify emerging trends and explore new avenues for investigation, facilitating easier scientific information retrieval. Many machine learning methods,…

Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualized word embeddings,…

In the burgeoning field of natural language processing (NLP), Neural Topic Models (NTMs) , Large Language Models (LLMs) and Diffusion model have emerged as areas of significant research interest. Despite this, NTMs primarily utilize…

Existing domain-specific Large Language Models (LLMs) are typically developed by fine-tuning general-purposed LLMs with large-scale domain-specific corpora. However, training on large-scale corpora often fails to effectively organize domain…

Neural topic models have triggered a surge of interest in extracting topics from text automatically since they avoid the sophisticated derivations in conventional topic models. However, scarce neural topic models incorporate the word…

The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…

The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model framework for multi-label text classification. Instead of…

Topic models can be useful tools to discover latent topics in collections of documents. Recent studies have shown the feasibility of approach topic modeling as a clustering task. We present BERTopic, a topic model that extends this process…

Data analysts have long sought to turn unstructured text data into meaningful concepts. Though common, topic modeling and clustering focus on lower-level keywords and require significant interpretative work. We introduce concept induction,…

Multi-label classification is a common supervised machine learning problem where each instance is associated with multiple classes. The key challenge in this problem is learning the correlations between the classes. An additional challenge…

Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the tea leaves" to interpret; additionally, they offer users…

Predicting and explaining the private information contained in an image in human-understandable terms is a complex and contextual task. This task is challenging even for large language models. To facilitate the understanding of privacy…

Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant…

Topic models are used to make sense of large text collections. However, automatically evaluating topic model output and determining the optimal number of topics both have been longstanding challenges, with no effective automated solutions…