Glyph2Vec: Learning Chinese Out-of-Vocabulary Word Embedding from Glyphs

Hong-You Chen, Sz-Han Yu, Shou-de Lin


Abstract
Chinese NLP applications that rely on large text often contain huge amounts of vocabulary which are sparse in corpus. We show that characters’ written form, Glyphs, in ideographic languages could carry rich semantics. We present a multi-modal model, Glyph2Vec, to tackle Chinese out-of-vocabulary word embedding problem. Glyph2Vec extracts visual features from word glyphs to expand current word embedding space for out-of-vocabulary word embedding, without the need of accessing any corpus, which is useful for improving Chinese NLP systems, especially for low-resource scenarios. Experiments across different applications show the significant effectiveness of our model.
Anthology ID:
2020.acl-main.256
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2865–2871
Language:
URL:
https://aclanthology.org/2020.acl-main.256
DOI:
10.18653/v1/2020.acl-main.256
Bibkey:
Cite (ACL):
Hong-You Chen, Sz-Han Yu, and Shou-de Lin. 2020. Glyph2Vec: Learning Chinese Out-of-Vocabulary Word Embedding from Glyphs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2865–2871, Online. Association for Computational Linguistics.
Cite (Informal):
Glyph2Vec: Learning Chinese Out-of-Vocabulary Word Embedding from Glyphs (Chen et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2020.acl-main.256.pdf
Video:
 http://slideslive.com/38928977