面向信息抽取的多源和多目标语言零样本跨语言迁移学习：语言选择与对抗训练
Zero-shot Cross-lingual Transfer Learning with Multiple Source and Target Languages for Information Extraction: Language Selection and Adversarial Training
AI总结：
研究多对多跨语言迁移学习，提出组合语言距离度量指导语言选择，并基于对抗训练提出关系迁移设置整合多语言无标签数据，提升多语言IE系统泛化能力。
摘要：
以往处理多语言IE的大多数研究局限于零样本跨语言单迁移（一对一）设置，且主要以高资源语言作为源训练数据。因此，这些工作对开发能够泛化到尽可能多语言的现实多语言IE系统目标提供的理解和益处甚微。本研究旨在通过分析覆盖多种语言的近期IE语料库的跨语言多可迁移性（多对多迁移学习）来填补这一空白。具体而言，我们首先确定单迁移性能与多种基于语言学的距离之间的相关性。基于所得见解，可以开发一种组合语言距离度量，它不仅高度相关，而且在不同任务和模型规模下具有鲁棒性。接下来，我们研究在训练和评估过程中涉及多种语言的更一般的零样本多语言迁移设置。基于新定义距离的语言聚类可以为数据（语言）选择问题中实现最佳成本性能权衡提供方向。最后，提出了一种关系迁移设置，通过基于对抗训练利用上述语言距离诱导的关系，进一步整合多语言无标签数据。
英文摘要：
The majority of previous researches addressing multi-lingual IE are limited to zero-shot cross-lingual single-transfer (one-to-one) setting, with high-resource languages predominantly as source training data. As a result, these works provide little understanding and benefit for the realistic goal of developing a multi-lingual IE system that can generalize to as many languages as possible. Our study aims to fill this gap by providing a detailed analysis on Cross-Lingual Multi-Transferability (many-to-many transfer learning), for the recent IE corpora that cover a diverse set of languages. Specifically, we first determine the correlation between single-transfer performance and a wide range of linguistic-based distances. From the obtained insights, a combined language distance metric can be developed that is not only highly correlated but also robust across different tasks and model scales. Next, we investigate the more general zero-shot multi-lingual transfer settings where multiple languages are involved in the training and evaluation processes. Language clustering based on the newly defined distance can provide directions for achieving the optimal cost-performance trade-off in data (languages) selection problem. Finally, a relational-transfer setting is proposed to further incorporate multi-lingual unlabeled data based on adversarial training using the relation induced from the above linguistic distance.
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。
