Selective Decoding for Cross-lingual Open Information Extraction

Sheng Zhang, Kevin Duh, Benjamin Van Durme


Abstract
Cross-lingual open information extraction is the task of distilling facts from the source language into representations in the target language. We propose a novel encoder-decoder model for this problem. It employs a novel selective decoding mechanism, which explicitly models the sequence labeling process as well as the sequence generation process on the decoder side. Compared to a standard encoder-decoder model, selective decoding significantly increases the performance on a Chinese-English cross-lingual open IE dataset by 3.87-4.49 BLEU and 1.91-5.92 F1. We also extend our approach to low-resource scenarios, and gain promising improvement.
Anthology ID:
I17-1084
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
832–842
Language:
URL:
https://aclanthology.org/I17-1084
DOI:
Bibkey:
Cite (ACL):
Sheng Zhang, Kevin Duh, and Benjamin Van Durme. 2017. Selective Decoding for Cross-lingual Open Information Extraction. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 832–842, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Selective Decoding for Cross-lingual Open Information Extraction (Zhang et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/I17-1084.pdf