A Truly Joint Neural Architecture for Segmentation and Parsing

Danit Yshaayahu Levi, Reut Tsarfaty


Abstract
Contemporary multilingual dependency parsers can parse a diverse set of languages, but for Morphologically Rich Languages (MRLs), performance is attested to be lower than other languages. The key challenge is that, due to high morphological complexity and ambiguity of the space-delimited input tokens, the linguistic units that act as nodes in the tree are not known in advance. Pre-neural dependency parsers for MRLs subscribed to the joint morpho-syntactic hypothesis, stating that morphological segmentation and syntactic parsing should be solved jointly, rather than as a pipeline where segmentation precedes parsing. However, neural state-of-the-art parsers to date use a strict pipeline. In this paper we introduce a joint neural architecture where a lattice-based representation preserving all morphological ambiguity of the input is provided to an arc-factored model, which then solves the morphological segmentation and syntactic parsing tasks at once. Our experiments on Hebrew, a rich and highly ambiguous MRL, demonstrate state-of-the-art performance on parsing, tagging and segmentation of the Hebrew section of UD, using a single model. This proposed architecture is LLM-based and language agnostic, providing a solid foundation for MRLs to obtain further performance improvements and bridge the gap with other languages.
Anthology ID:
2024.eacl-long.84
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1408–1420
Language:
URL:
https://aclanthology.org/2024.eacl-long.84
DOI:
Bibkey:
Cite (ACL):
Danit Yshaayahu Levi and Reut Tsarfaty. 2024. A Truly Joint Neural Architecture for Segmentation and Parsing. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1408–1420, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
A Truly Joint Neural Architecture for Segmentation and Parsing (Yshaayahu Levi & Tsarfaty, EACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eacl-long.84.pdf
Video:
 https://aclanthology.org/2024.eacl-long.84.mp4