@inproceedings{L16-1138,
 abstract = {Chinese sentences are written as sequences of characters, which are elementary units of syntax and semantics. Characters are highly polysemous in forming words. We present a position-sensitive skip-gram model to learn multi-prototype Chinese character embeddings, and explore the usefulness of such character embeddings to Chinese NLP tasks. Evaluation on character similarity shows that multi-prototype embeddings are significantly better than a single-prototype baseline. In addition, used as features in the Chinese NER task, the embeddings result in a 1.74\% F-score improvement over a state-of-the-art baseline.
},
 address = {Portorož, Slovenia},
 author = {Yanan Lu and Yue Zhang and Donghong Ji},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {855--859},
 publisher = {European Language Resources Association (ELRA)},
 title = {Multi-prototype Chinese Character Embedding},
 url = {https://www.aclweb.org/anthology/L16-1138},
 year = {2016}
}