XTRA通过双对齐机制提升多语言主题模型的连贯性与一致性。
XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments
- 用对比学习对齐文档-主题分布，实现跨语言语义空间统一。
- 将词-主题分布投影至同一空间，提升主题跨语言一致性。
- 在多个语料库上超越基线，在连贯性、多样性与对齐质量上均领先。
跨语言主题建模旨在发现不同语言间的共享语义主题。尽管已有方法在提升主题多样性方面取得进展，但通常难以保证高主题连贯性及跨语言的一致性。本文提出XTRA（基于主题与表征对齐的跨语言主题建模），将词袋模型与多语言嵌入统一。该框架包含两个核心组件：(1) 表征对齐，通过对比学习在共享语义空间中对齐文档-主题分布；(2) 主题对齐，将词-主题分布投影至同一空间，以强制跨语言一致性。双重机制使XTRA能学习到可解释性强（连贯且多样）且跨语言一致的主题。在多语言语料库上的实验表明，XTRA显著优于强基线，在主题连贯性、多样性及对齐质量上均有提升。代码与可复现脚本已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。