Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing

Jingfeng Yang, Federico Fancellu, Bonnie Webber, Diyi Yang


Abstract
The availability of corpora has led to significant advances in training semantic parsers in English. Unfortunately, for languages other than English, annotated data is limited and so is the performance of the developed parsers. Recently, pretrained multilingual models have been proven useful for zero-shot cross-lingual transfer in many NLP tasks. What else does it require to apply a parser trained in English to other languages for zero-shot cross-lingual semantic parsing? Will simple language-independent features help? To this end, we experiment with six Discourse Representation Structure (DRS) semantic parsers in English, and generalize them to Italian, German and Dutch, where there are only a small number of manually annotated parses available. Extensive experiments show that despite its simplicity, adding Universal Dependency (UD) relations and Universal POS tags (UPOS) as model-agnostic features achieves surprisingly strong improvement on all parsers.
Anthology ID:
2021.emnlp-main.472
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5848–5856
Language:
URL:
https://aclanthology.org/2021.emnlp-main.472
DOI:
10.18653/v1/2021.emnlp-main.472
Bibkey:
Cite (ACL):
Jingfeng Yang, Federico Fancellu, Bonnie Webber, and Diyi Yang. 2021. Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5848–5856, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing (Yang et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.472.pdf
Software:
 2021.emnlp-main.472.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.472.mp4
Code
 gt-salt/multilingual-drs-semantic-parsing