Skip to Main content Skip to Navigation
Conference papers

Deeper syntax for better semantic parsing

Abstract : Syntax plays an important role in the task of predicting the semantic structure of a sentence. But syntactic phenomena such as alternations, control and raising tend to obfuscate the relation between syntax and semantics. In this paper we predict the semantic structure of a sentence using a deeper syntax than what is usually done. This deep syntactic representation abstracts away from purely syntactic phenomena and proposes a structural organization of the sentence that is closer to the semantic representation. Experiments conducted on a French corpus annotated with semantic frames showed that a semantic parser reaches better performances with such a deep syntactic input.
Complete list of metadatas

Cited literature [34 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01391678
Contributor : Olivier Michalon <>
Submitted on : Tuesday, November 8, 2016 - 10:14:30 AM
Last modification on : Friday, March 27, 2020 - 3:16:36 AM
Document(s) archivé(s) le : Tuesday, March 14, 2017 - 10:43:00 PM

File

coling2016_deepsynt.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : hal-01391678, version 1

Citation

Olivier Michalon, Corentin Ribeyre, Marie Candito, Alexis Nasr. Deeper syntax for better semantic parsing. Coling 2016 - 26th International Conference on Computational Linguistics, Dec 2016, Osaka, Japan. ⟨hal-01391678⟩

Share

Metrics

Record views

761

Files downloads

421