mCL-NER：基于多视角对比学习的跨语言命名实体识别
mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning
AI总结：
本文提出 mCL-NER，通过多视角对比学习对齐语义和词元关系表示，并结合自训练，在 XTREME 基准 40 种语言上显著提升跨语言命名实体识别性能。
摘要：
跨语言命名实体识别（CrossNER）面临因多语言语料稀缺而导致的性能不均衡挑战，尤其是对非英语数据而言。以往工作主要聚焦于数据驱动的迁移方法，但一个尚未被充分探索的重要方面是对齐不同语言之间的语义表示和词元级表示。在本文中，我们提出面向跨语言命名实体识别的多视角对比学习（mCL-NER）。具体而言，我们将 CrossNER 任务重新构建为识别词元对之间关系的问题。该方法利用实体内部词元到词元连接所固有的上下文细微差别，使我们能够对齐不同语言之间的表示。我们引入了一个多视角对比学习框架，涵盖源语言、语码转换和目标语言句子之间的语义对比，以及词元到词元关系之间的对比。通过在语义空间和关系空间中强制一致性，我们最小化了源句子与其语码转换对应句及目标语言对应句之间的差距。这种对齐还延伸到不同词元之间的关系，增强了实体跨语言的投影能力。我们进一步通过将自训练与有标注源数据和未标注目标数据相结合来增强 CrossNER。我们在覆盖 40 种语言的 XTREME 基准上的实验表明，mCL-NER 优于以往的数据驱动方法和基于模型的方法。它在广泛的范围内实现了接近 +2.0 $F_1$ 分数的显著提升，并确立了新的最先进性能。
英文摘要：
Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora, especially for non-English data. While prior efforts mainly focus on data-driven transfer methods, a significant aspect that has not been fully explored is aligning both semantic and token-level representations across diverse languages. In this paper, we propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (mCL-NER). Specifically, we reframe the CrossNER task into a problem of recognizing relationships between pairs of tokens. This approach taps into the inherent contextual nuances of token-to-token connections within entities, allowing us to align representations across different languages. A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations. By enforcing agreement within both semantic and relational spaces, we minimize the gap between source sentences and their counterparts of both codeswitched and target sentences. This alignment extends to the relationships between diverse tokens, enhancing the projection of entities across languages. We further augment CrossNER by combining self-training with labeled source data and unlabeled target data. Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of mCL-NER over prior data-driven and model-based approaches. It achieves a substantial increase of nearly +2.0 $F_1$ scores across a broad spectrum and establishes itself as the new state-of-the-art performer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
