Related papers: Multilingual Topic Models for Unaligned Text

Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…

Continued pretraining and instruction tuning on large-scale multilingual data have proven to be effective in scaling large language models (LLMs) to low-resource languages. However, the unaligned nature of such data limits its ability to…

Cross-lingual topic modeling seeks to uncover coherent and semantically aligned topics across languages - a task central to multilingual understanding. Yet most existing models learn topics in disjoint, language-specific spaces and rely on…

Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. Recent LLM-based refinements improve…

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

Topic evolution modeling has received significant attentions in recent decades. Although various topic evolution models have been proposed, most studies focus on the single document corpus. However in practice, we can easily access data…

In this paper, we present the Polylingual Labeled Topic Model, a model which combines the characteristics of the existing Polylingual Topic Model and Labeled LDA. The model accounts for multiple languages with separate topic distributions…

Topic modeling analyzes documents to learn meaningful patterns of words. For documents collected in sequence, dynamic topic models capture how these patterns vary over time. We develop the dynamic embedded topic model (D-ETM), a generative…

A recent line of work in natural language processing has aimed to combine language models and topic models. These topic-guided language models augment neural language models with topic models, unsupervised learning methods that can discover…

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its…

Topic models have evolved from conventional Bayesian probabilistic models to recent Neural Topic Models (NTMs). Although NTMs have shown promising performance when trained and tested on a specific corpus, their generalisation ability across…

Topic models provide a useful text-mining tool for learning, extracting, and discovering latent structures in large text corpora. Although a plethora of methods have been proposed for topic modeling, lacking in the literature is a formal…

Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable,…

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We…

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

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…

One of the challenges for text analysis in medical domains is analyzing large-scale medical documents. As a consequence, finding relevant documents has become more difficult. One of the popular methods to retrieve information based on…

Traditional topic models are effective at uncovering latent themes in large text collections. However, due to their reliance on bag-of-words representations, they struggle to capture semantically abstract features. While some neural…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…