Lune

EMNLP Findings2025

ProtoXTM: Cross-Lingual Topic Modeling with Document-Level Prototype-based Contrastive Learning

Seung-Won Seo, Soon-Sun Kwon

Abstract

Cross-Lingual Topic Modeling (CLTM) is an essential task in the field of data mining and natural language processing, aiming to extract aligned and semantically coherent topics from bilingual corpora. Recent advances in crosslingual neural topic models have widely leveraged bilingual dictionaries to achieve wordlevel topic alignment. However, two critical challenges remain in cross-lingual topic modeling, the topic mismatch issue and the degeneration of intra-lingual topic interpretability. Due to linguistic diversity, some translated word pairs may not represent semantically coherent topics despite being lexical equivalents, and the objective of cross-lingual topic alignment in CLTM can consequently degrade topic interpretability within each intralanguages. To address these issues, we propose a novel document-level prototype-based contrastive learning paradigm for cross-lingual topic modeling. Additionally, we design a retrieval-based positive sampling strategy for contrastive learning without data augmentation. Furthermore, we introduce ProtoXTM, a crosslingual neural topic model based on documentlevel prototype-based contrastive learning. Extensive experiments indicate that our approach achieves state-of-the-art performance on crosslingual and mono-lingual benchmarks, demonstrating enhanced topic interpretability.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Contrastive Learning for Neural Topic Model cites A Simple Framework for Contrastive Learning of Visual Representations
  • Effective Neural Topic Modeling with Embedding Clustering Regularization cites Contrastive Learning for Neural Topic Model
  • Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning cites A Simple Framework for Contrastive Learning of Visual Representations
  • Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning cites Prototypical Contrastive Learning of Unsupervised Representations
  • Prototypical Contrastive Learning of Unsupervised Representations cites Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
  • Prototypical Contrastive Learning of Unsupervised Representations cites A Simple Framework for Contrastive Learning of Visual Representations
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on12

  1. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  2. Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningJean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec et al.NeurIPS 2020 · 9,171 citations
  3. Prototypical Contrastive Learning of Unsupervised RepresentationsJunnan Li, Pan Zhou, Caiming Xiong, Steven C. H. HoiICLR 2021 · 484 citations
  4. Effective Neural Topic Modeling with Embedding Clustering RegularizationXiaobao Wu, Xinshuai Dong, Thong Thanh Nguyen, Anh Tuan LuuICML 2023 · 87 citations
  5. Contrastive Learning for Neural Topic ModelThong Nguyen, Anh Tuan LuuNeurIPS 2021 · 82 citations

Related papers

  1. XTRA: Cross-Lingual Topic Modeling with Topic and Representation AlignmentsTien-Phat Nguyen, Vu Minh Ngo, Tung Nguyen, Linh Ngo Van et al.EMNLP Findings 2025 · 1 citation
  2. InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic ModelingXiaobao Wu, Xinshuai Dong, Thong Nguyen, Chaoqun Liu et al.AAAI 2023 · 35 citations
  3. GloCTM: Cross-Lingual Topic Modeling via a Global Context SpaceNguyen Tien Phat, Ngo Vu Minh, Linh Ngo Van, Nguyen Thi Ngoc Diep et al.AAAI 2026 · 2 citations
  4. NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive PretrainingSicheng Wang, Wenyi Wu, Zibo ZhangEMNLP Findings 2025 · 1 citation
  5. LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language ModelsMinh Chu Xuan, Tien-Phat Nguyen, Linh Ngo Van, Dinh Viet Sang et al.ACL 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines