A Hybrid Learning Scheme for Chinese Word Embedding

Wenfan Chen, Weiguo Sheng


Abstract
To improve word embedding, subword information has been widely employed in state-of-the-art methods. These methods can be classified to either compositional or predictive models. In this paper, we propose a hybrid learning scheme, which integrates compositional and predictive model for word embedding. Such a scheme can take advantage of both models, thus effectively learning word embedding. The proposed scheme has been applied to learn word representation on Chinese. Our results show that the proposed scheme can significantly improve the performance of word embedding in terms of analogical reasoning and is robust to the size of training data.
Anthology ID:
W18-3011
Volume:
Proceedings of the Third Workshop on Representation Learning for NLP
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Kiros, Hongyuan Mei, Dipendra Misra
Venue:
RepL4NLP
SIG:
SIGREP
Publisher:
Association for Computational Linguistics
Note:
Pages:
84–90
Language:
URL:
https://aclanthology.org/W18-3011
DOI:
10.18653/v1/W18-3011
Bibkey:
Cite (ACL):
Wenfan Chen and Weiguo Sheng. 2018. A Hybrid Learning Scheme for Chinese Word Embedding. In Proceedings of the Third Workshop on Representation Learning for NLP, pages 84–90, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
A Hybrid Learning Scheme for Chinese Word Embedding (Chen & Sheng, RepL4NLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-3011.pdf