Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings
TL
TL;DR
A new corpus of Weibo messages annotated for both name and nominal mentions is presented and a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text is proposed.
Abstract
We consider the task of named entity recognition for Chinese social media. The long line of work in Chinese NER has focused on formal domains, and NER for social media has been largely restricted to English. We present a new corpus of Weibo messages annotated for both name and nominal mentions. Additionally, we evaluate three types of neural embeddings for representing Chinese text. Finally, we propose a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text. Our methods yield a 9% improvement over a stateof-the-art baseline.
References42 items
1
Joint Learning of Character and Word Embeddings
2
Learning Composition Models for Phrase Embeddings
3
Domain-Specific Product Named Entity Recognition from Chinese Microblog
4
Co-learning of Word Representations and Morpheme Representations
5