Graph- and surface-level sentence chunking
Authors
Muszynska, Ewa
Publication Date
2016-08-12Journal Title
Proceedings of the ACL 2016 Student Research Workshop
Conference Name
54th Annual Meeting of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Pages
93-99
Language
English
Type
Conference Object
This Version
VoR
Metadata
Show full item recordCitation
Muszynska, E. (2016). Graph- and surface-level sentence chunking. Proceedings of the ACL 2016 Student Research Workshop, 93-99. https://doi.org/10.17863/CAM.9727
Abstract
The computing cost of many NLP tasks increases faster than linearly with the length of the representation of a sentence. For parsing the representation is tokens, while for operations on syntax and semantics it will be more complex. In this paper we propose a new task of $\textit{sentence chunking}$: splitting sentence representations into coherent substructures. Its aim is to make further processing of long sentences more tractable. We investigate this idea experimentally using the Dependency Minimal Recursion Semantics (DMRS) representation.
Sponsorship
EPSRC
Embargo Lift Date
2100-01-01
Identifiers
External DOI: https://doi.org/10.17863/CAM.9727
This record's URL: https://www.repository.cam.ac.uk/handle/1810/264292
Rights
Attribution 4.0 International, Attribution 4.0 International, Attribution 4.0 International
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.