The effect of syntactic representation on semantic role labeling
(2008) International Conference on Computational Linguistics (Coling) p.393-400- Abstract
- Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design
decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based representations for SRL of English in the FrameNet paradigm.
Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform
slightly higher on... (More) - Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design
decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based representations for SRL of English in the FrameNet paradigm.
Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform
slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1229591
- author
- Johansson, Richard
LU
and Nugues, Pierre
LU
- organization
- publishing date
- 2008
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- syntactic representation, Natural language processing, semantic analysis
- host publication
- Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)
- pages
- 8 pages
- publisher
- Association for Computational Linguistics
- conference name
- International Conference on Computational Linguistics (Coling)
- conference dates
- 2008-08-18 - 2008-08-22
- external identifiers
-
- scopus:79960277348
- language
- English
- LU publication?
- yes
- id
- e5f44323-9024-4cc5-9f3d-538212ebf402 (old id 1229591)
- date added to LUP
- 2016-04-04 10:33:32
- date last changed
- 2022-04-23 23:09:46
@inproceedings{e5f44323-9024-4cc5-9f3d-538212ebf402, abstract = {{Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design<br/><br> decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based representations for SRL of English in the FrameNet paradigm.<br/><br> <br/><br> Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform<br/><br> slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.}}, author = {{Johansson, Richard and Nugues, Pierre}}, booktitle = {{Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)}}, keywords = {{syntactic representation; Natural language processing; semantic analysis}}, language = {{eng}}, pages = {{393--400}}, publisher = {{Association for Computational Linguistics}}, title = {{The effect of syntactic representation on semantic role labeling}}, url = {{https://lup.lub.lu.se/search/files/5567253/1229594.pdf}}, year = {{2008}}, }