Related papers: Coherence-Aware Neural Topic Modeling

Model interpretability has become an important problem in machine learning (ML) due to the increased effect that algorithmic decisions have on humans. Counterfactual explanations can help users understand not only why ML models make certain…

Topic modeling seeks to uncover latent semantic structure in text corpora with minimal supervision. Neural approaches achieve strong performance but require extensive tuning and struggle with lifelong learning due to catastrophic forgetting…

Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…

Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of…

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

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…

Topic modeling is a state-of-the-art technique for analyzing text corpora. It uses a statistical model, most commonly Latent Dirichlet Allocation (LDA), to discover abstract topics that occur in the document collection. However, the…

We investigate mathematically the notion of incoherence: a structural issue with reinforcement learning policies derived by naive goal-conditioning of autoregressive models. We focus on the process of re-training models on their own…

Certain type of documents such as tweets are collected by specifying a set of keywords. As topics of interest change with time it is beneficial to adjust keywords dynamically. The challenge is that these need to be specified ahead of…

Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm…

Machine reading comprehension is a heavily-studied research and test field for evaluating new pre-trained language models (PrLMs) and fine-tuning strategies, and recent studies have enriched the pre-trained language models with syntactic,…

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to…

Contextualised word vectors obtained via pre-trained language models encode a variety of knowledge that has already been exploited in applications. Complementary to these language models are probabilistic topic models that learn thematic…

Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult. Provable guarantees for unlearning are often limited to…

To improve the trustworthiness of an AI model, finding consistent, understandable representations of its inference process is essential. This understanding is particularly important in high-stakes operations such as weather forecasting,…

Providing natural language explanations for recommendations is particularly useful from the perspective of a non-expert user. Although several methods for providing such explanations have recently been proposed, we argue that an important…

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…

In this paper, we provide the first practical algorithms with provable guarantees for the problem of inferring the topics assigned to each document in an LDA topic model. This is the primary inference problem for many applications of topic…

We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large vision language…