CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages

Pretam Ray, Jivnesh Sandhan, Amrith Krishna, Pawan Goyal


Abstract
Neural dependency parsing has achieved remarkable performance for low resource morphologically rich languages. It has also been well-studied that morphologically rich languages exhibit relatively free word order. This prompts a fundamental investigation: Is there a way to enhance dependency parsing performance, making the model robust to word order variations utilizing the relatively free word order nature of morphologically rich languages? In this work, we examine the robustness of graph-based parsing architectures on 7 relatively free word order languages. We focus on scrutinizing essential modifications such as data augmentation and the removal of position encoding required to adapt these architectures accordingly. To this end, we propose a contrastive self-supervised learning method to make the model robust to word order variations. Furthermore, our proposed modification demonstrates a substantial average gain of 3.03/2.95 points in 7 relatively free word order languages, as measured by the UAS/LAS Score metric when compared to the best performing baseline.
Anthology ID:
2024.emnlp-main.482
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8458–8466
Language:
URL:
https://aclanthology.org/2024.emnlp-main.482
DOI:
Bibkey:
Cite (ACL):
Pretam Ray, Jivnesh Sandhan, Amrith Krishna, and Pawan Goyal. 2024. CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8458–8466, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages (Ray et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.482.pdf