Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction

Hongyuan Mei, Sheng Zhang, Kevin Duh, Benjamin Van Durme


Abstract
Cross-lingual information extraction (CLIE) is an important and challenging task, especially in low resource scenarios. To tackle this challenge, we propose a training method, called Halo, which enforces the local region of each hidden state of a neural model to only generate target tokens with the same semantic structure tag. This simple but powerful technique enables a neural model to learn semantics-aware representations that are robust to noise, without introducing any extra parameter, thus yielding better generalization in both high and low resource settings.
Anthology ID:
S18-2017
Volume:
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Malvina Nissim, Jonathan Berant, Alessandro Lenci
Venue:
*SEM
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
142–147
Language:
URL:
https://aclanthology.org/S18-2017
DOI:
10.18653/v1/S18-2017
Bibkey:
Cite (ACL):
Hongyuan Mei, Sheng Zhang, Kevin Duh, and Benjamin Van Durme. 2018. Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 142–147, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction (Mei et al., *SEM 2018)
Copy Citation:
PDF:
https://aclanthology.org/S18-2017.pdf