相关论文: Beyond the Black Box: Integrating Lexical and Sema…

While there has been substantial progress in text comprehension through simple factoid question answering, more holistic comprehension of a discourse still presents a major challenge (Dunietz et al., 2020). Someone critically reflecting on…

Marrying topic models and language models exposes language understanding to a broader source of document-level context beyond sentences via topics. While introducing topical semantics in language models, existing approaches incorporate…

During the last fifteen years, automatic text scaling has become one of the key tools of the Text as Data community in political science. Prominent text scaling algorithms, however, rely on the assumption that latent positions can be…

This study compares the effectiveness of BERTopic and Probabilistic Latent Semantic Analysis (PLSA) in extracting meaningful topics from aviation safety reports aiming to enhance the understanding of patterns in aviation incident data.…

Purpose: Multicriteria decision analysis (MCDA) has become increasingly essential for decision-making in complex environments. In response to this need, the pyDecision library, implemented in Python and available at https://bit.ly/3tLFGtH,…

This study applies BERTopic, a transformer-based topic modeling technique, to the lmsys-chat-1m dataset, a multilingual conversational corpus built from head-to-head evaluations of large language models (LLMs). Each user prompt is paired…

While large language models (LLMs) have advanced the field of natural language processing (NLP), their "black box" nature obscures their decision-making processes. To address this, researchers developed structured approaches using higher…

Topic modeling extracts latent themes from large text collections, but leading approaches like BERTopic face critical limitations: stochastic instability, loss of lexical precision ("Embedding Blur"), and reliance on a single data…

As short text data in native languages like Hindi increasingly appear in modern media, robust methods for topic modeling on such data have gained importance. This study investigates the performance of BERTopic in modeling Hindi short texts,…

This paper presents the results of the first application of BERTopic, a state-of-the-art topic modeling technique, to short text written in a morphologi-cally rich language. We applied BERTopic with three multilingual embed-ding models on…

To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC. Compared with existing CQA datasets, PACIFIC exhibits three key features: (i) proactivity, (ii) numerical…

The growing number of languages considered in multilingual NLP, including new datasets and tasks, poses challenges regarding properly and accurately reporting which languages are used and how. For example, datasets often use different…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Interpreting the internal behavior of large language models trained on code remains a critical challenge, particularly for applications demanding trust, transparency, and semantic robustness. We propose Code Concept Analysis (CoCoA): a…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study,…

Like humans, document summarization models can interpret a document's contents in a number of ways. Unfortunately, the neural models of today are largely black boxes that provide little explanation of how or why they generated a summary in…

Knowledge distillation (KD) methods are pivotal in compressing large pre-trained language models into smaller models, ensuring computational efficiency without significantly dropping performance. Traditional KD techniques assume homogeneity…

AI systems' ability to explain their reasoning is critical to their utility and trustworthiness. Deep neural networks have enabled significant progress on many challenging problems such as visual question answering (VQA). However, most of…

Pre-trained language models have led to a new state-of-the-art in many NLP tasks. However, for topic modeling, statistical generative models such as LDA are still prevalent, which do not easily allow incorporating contextual word vectors.…