Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection
This addresses the challenge of expensive and time-consuming manual annotation for NER in new languages, offering a practical solution for multilingual NLP applications, though it is incremental in combining existing projection ideas.
The paper tackles the problem of cross-lingual named entity recognition without human annotation in target languages by proposing two weakly supervised approaches: automatic annotation projection and word embedding projection, combined via co-decoding schemes. The results show that the combined systems outperform three other weakly supervised approaches on CoNLL data.
The state-of-the-art named entity recognition (NER) systems are supervised machine learning models that require large amounts of manually annotated data to achieve high accuracy. However, annotating NER data by human is expensive and time-consuming, and can be quite difficult for a new language. In this paper, we present two weakly supervised approaches for cross-lingual NER with no human annotation in a target language. The first approach is to create automatically labeled NER data for a target language via annotation projection on comparable corpora, where we develop a heuristic scheme that effectively selects good-quality projection-labeled data from noisy data. The second approach is to project distributed representations of words (word embeddings) from a target language to a source language, so that the source-language NER system can be applied to the target language without re-training. We also design two co-decoding schemes that effectively combine the outputs of the two projection-based approaches. We evaluate the performance of the proposed approaches on both in-house and open NER data for several target languages. The results show that the combined systems outperform three other weakly supervised approaches on the CoNLL data.