Content Differences in Syntactic and Semantic Representation

Daniel Hershcovich, Omri Abend, Ari Rappoport


Abstract
Syntactic analysis plays an important role in semantic parsing, but the nature of this role remains a topic of ongoing debate. The debate has been constrained by the scarcity of empirical comparative studies between syntactic and semantic schemes, which hinders the development of parsing methods informed by the details of target schemes and constructions. We target this gap, and take Universal Dependencies (UD) and UCCA as a test case. After abstracting away from differences of convention or formalism, we find that most content divergences can be ascribed to: (1) UCCA’s distinction between a Scene and a non-Scene; (2) UCCA’s distinction between primary relations, secondary ones and participants; (3) different treatment of multi-word expressions, and (4) different treatment of inter-clause linkage. We further discuss the long tail of cases where the two schemes take markedly different approaches. Finally, we show that the proposed comparison methodology can be used for fine-grained evaluation of UCCA parsing, highlighting both challenges and potential sources for improvement. The substantial differences between the schemes suggest that semantic parsers are likely to benefit downstream text understanding applications beyond their syntactic counterparts.
Anthology ID:
N19-1047
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
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
478–488
Language:
URL:
https://aclanthology.org/N19-1047
DOI:
10.18653/v1/N19-1047
Bibkey:
Cite (ACL):
Daniel Hershcovich, Omri Abend, and Ari Rappoport. 2019. Content Differences in Syntactic and Semantic Representation. 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 478–488, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Content Differences in Syntactic and Semantic Representation (Hershcovich et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/N19-1047.pdf
Software:
 N19-1047.Software.zip
Supplementary:
 N19-1047.Supplementary.pdf
Poster:
 N19-1047.Poster.pdf
Code
 UniversalConceptualCognitiveAnnotation/UCCA_English-EWT +  additional community code
Data
English Web TreebankUniversal Dependencies