Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition
Genta Indra Winata, Chien-Sheng Wu, Andrea Madotto, Pascale Fung
Abstract
We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and transfer learning to address out-of-vocabulary words. In order to mitigate data noise, we propose to use token replacement and normalization. In the 3rd Workshop on Computational Approaches to Linguistic Code-Switching Shared Task, we achieved second place with 62.76% harmonic mean F1-score for English-Spanish language pair without using any gazetteer and knowledge-based information.- Anthology ID:
- W18-3214
- Volume:
- Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 110–114
- Language:
- URL:
- https://aclanthology.org/W18-3214
- DOI:
- 10.18653/v1/W18-3214
- Cite (ACL):
- Genta Indra Winata, Chien-Sheng Wu, Andrea Madotto, and Pascale Fung. 2018. Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition. In Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching, pages 110–114, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition (Winata et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/W18-3214.pdf