Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations

Abstract

Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching. Such requirements and assumptions are infeasible for most languages, especially for languages with large linguistic distances, e.g., English and Chinese. In this work, we propose a Multilingual Language Model with deep semantic Alignment (MLMA) to generate language-independent representations for cross-lingual sequence labeling. Our methods require only monolingual corpora with no bilingual resources at all and take advantage of deep contextualized representations. Experimental results show that our approach achieves new state-of-the-art NER and POS performance across European languages, and is also effective on distant language pairs such as English and Chinese.

Accepted at EMNLP 2019

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Deep Domain Confusion: Maximizing for Domain Invariance
• NLTK: The Natural Language Toolkit
• Word Translation Without Parallel Data
• Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection
• Demystifying Neural Style Transfer
• Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
• Neural Cross-Lingual Named Entity Recognition with Minimal Resources