On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing

Wasi Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang, Nanyun Peng


Abstract
Different languages might have different word orders. In this paper, we investigate crosslingual transfer and posit that an orderagnostic model will perform better when transferring to distant foreign languages. To test our hypothesis, we train dependency parsers on an English corpus and evaluate their transfer performance on 30 other languages. Specifically, we compare encoders and decoders based on Recurrent Neural Networks (RNNs) and modified self-attentive architectures. The former relies on sequential information while the latter is more flexible at modeling word order. Rigorous experiments and detailed analysis shows that RNN-based architectures transfer well to languages that are close to English, while self-attentive models have better overall cross-lingual transferability and perform especially well on distant languages.
Anthology ID:
N19-1253
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2440–2452
Language:
URL:
https://aclanthology.org/N19-1253
DOI:
10.18653/v1/N19-1253
Bibkey:
Cite (ACL):
Wasi Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang, and Nanyun Peng. 2019. On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2440–2452, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing (Ahmad et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/N19-1253.pdf
Supplementary:
 N19-1253.Supplementary.pdf
Code
 uclanlp/CrossLingualDepParser +  additional community code