XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments

• URL: http://arxiv.org/abs/2510.02788v1
• Date: Fri, 03 Oct 2025 07:46:23 GMT
• Title: XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments
• Authors: Tien Phat Nguyen, Vu Minh Ngo, Tung Nguyen, Linh Van Ngo, Duc Anh Nguyen, Sang Dinh, Trung Le,
• Abstract summary: Cross-lingual topic modeling aims to uncover shared semantic themes across languages.<n>We propose XTRA, a framework that unifies Bag-of-Words modeling with multilingual embeddings.<n>XTRA learns topics that are interpretable (coherent and diverse) and well-aligned across languages.
• Score: 16.831512837465123
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-lingual topic modeling aims to uncover shared semantic themes across languages. Several methods have been proposed to address this problem, leveraging both traditional and neural approaches. While previous methods have achieved some improvements in topic diversity, they often struggle to ensure high topic coherence and consistent alignment across languages. We propose XTRA (Cross-Lingual Topic Modeling with Topic and Representation Alignments), a novel framework that unifies Bag-of-Words modeling with multilingual embeddings. XTRA introduces two core components: (1) representation alignment, aligning document-topic distributions via contrastive learning in a shared semantic space; and (2) topic alignment, projecting topic-word distributions into the same space to enforce crosslingual consistency. This dual mechanism enables XTRA to learn topics that are interpretable (coherent and diverse) and well-aligned across languages. Experiments on multilingual corpora confirm that XTRA significantly outperforms strong baselines in topic coherence, diversity, and alignment quality. Code and reproducible scripts are available at https: //github.com/tienphat140205/XTRA.

Related papers

• GloCTM: Cross-Lingual Topic Modeling via a Global Context Space [28.89996742581612]
  GloCTM is a novel framework that enforces cross-lingual topic alignment through a unified semantic space spanning the entire model pipeline.<n>At the output level, the global topic-word distribution, defined over the combined vocabulary, structurally synchronizes topic meanings across languages.
  arXiv  Detail & Related papers  (2026-01-17T01:45:31Z)
• Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning [81.43257201833154]
  We propose Bi-IRRA: a Bidirectional Implicit Relation Reasoning and Aligning framework to learn alignment across languages and modalities.<n>Within Bi-IRRA, a bidirectional implicit relation reasoning module enables bidirectional prediction of masked image and text.<n>The proposed method achieves new state-of-the-art results on all multilingual TIPR datasets.
  arXiv  Detail & Related papers  (2025-10-20T16:01:11Z)
• HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling [4.8342038441006805]
  This paper introduces HAMLET, a graph-driven architecture for cross-lingual healthcare topic modeling.<n>The proposed approach uses neural-enhanced semantic fusion to refine the embeddings of topics generated by the Large Language Models.<n> Experiments were conducted using two healthcare datasets, one in English and one in French, from which six sets were derived.
  arXiv  Detail & Related papers  (2025-05-12T00:31:36Z)
• Multilingual Topic Classification in X: Dataset and Analysis [19.725017254962918]
  We introduce X-Topic, a multilingual dataset featuring content in four distinct languages (English, Spanish, Japanese, and Greek) Our dataset includes a wide range of topics, tailored for social media content, making it a valuable resource for scientists and professionals working on cross-linguistic analysis.
  arXiv  Detail & Related papers  (2024-10-04T01:37:26Z)
• Understanding Cross-Lingual Alignment -- A Survey [52.572071017877704]
  Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models. We survey the literature of techniques to improve cross-lingual alignment, providing a taxonomy of methods and summarising insights from throughout the field.
  arXiv  Detail & Related papers  (2024-04-09T11:39:53Z)
• mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning [54.523172171533645]
  Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora. We propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (mCL-NER) Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of mCL-NER over prior data-driven and model-based approaches.
  arXiv  Detail & Related papers  (2023-08-17T16:02:29Z)
• VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning [56.47303426167584]
  We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
  arXiv  Detail & Related papers  (2023-04-17T12:23:41Z)
• InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling [40.54497836775837]
  Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing aligned latent topics. Most existing methods suffer from producing repetitive topics that hinder further analysis and performance decline caused by low-coverage dictionaries. We propose the Cross-lingual Topic Modeling with Mutual Information (InfoCTM) to produce more coherent, diverse, and well-aligned topics.
  arXiv  Detail & Related papers  (2023-04-07T08:49:43Z)
• Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment [63.0407314271459]
  The proposed Cross-Align achieves the state-of-the-art (SOTA) performance on four out of five language pairs. Experiments show that the proposed Cross-Align achieves the state-of-the-art (SOTA) performance on four out of five language pairs.
  arXiv  Detail & Related papers  (2022-10-09T02:24:35Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.