Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit

Amrith Krishna, Ashim Gupta, Deepak Garasangi, Pavankumar Satuluri, Pawan Goyal


Abstract
Morphologically rich languages seem to benefit from joint processing of morphology and syntax, as compared to pipeline architectures. We propose a graph-based model for joint morphological parsing and dependency parsing in Sanskrit. Here, we extend the Energy based model framework (Krishna et al., 2020), proposed for several structured prediction tasks in Sanskrit, in 2 simple yet significant ways. First, the framework’s default input graph generation method is modified to generate a multigraph, which enables the use of an exact search inference. Second, we prune the input search space using a linguistically motivated approach, rooted in the traditional grammatical analysis of Sanskrit. Our experiments show that the morphological parsing from our joint model outperforms standalone morphological parsers. We report state of the art results in morphological parsing, and in dependency parsing, both in standalone (with gold morphological tags) and joint morphosyntactic parsing setting.
Anthology ID:
2020.emnlp-main.388
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4791–4797
Language:
URL:
https://aclanthology.org/2020.emnlp-main.388
DOI:
10.18653/v1/2020.emnlp-main.388
Bibkey:
Cite (ACL):
Amrith Krishna, Ashim Gupta, Deepak Garasangi, Pavankumar Satuluri, and Pawan Goyal. 2020. Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4791–4797, Online. Association for Computational Linguistics.
Cite (Informal):
Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit (Krishna et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.388.pdf
Optional supplementary material:
 2020.emnlp-main.388.OptionalSupplementaryMaterial.pdf
Video:
 https://slideslive.com/38938873