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.- Anthology ID:
- L16-1138
- Volume:
- Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
- Month:
- May
- Year:
- 2016
- Address:
- Portorož, Slovenia
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- 855–859
- Language:
- URL:
- https://aclanthology.org/L16-1138
- DOI:
- Cite (ACL):
- Yanan Lu, Yue Zhang, and Donghong Ji. 2016. Multi-prototype Chinese Character Embedding. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 855–859, Portorož, Slovenia. European Language Resources Association (ELRA).
- Cite (Informal):
- Multi-prototype Chinese Character Embedding (Lu et al., LREC 2016)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/L16-1138.pdf