Combining dependency information and generalization in a pattern-based approach to the classification of lexical-semantic relation instances

Silvia Necşulescu, Sara Mendes, Núria Bel

Abstract
This work addresses the classification of word pairs as instances of lexical-semantic relations. The classification is approached by leveraging patterns of co-occurrence contexts from corpus data. The significance of using dependency information, of augmenting the set of dependency paths provided to the system, and of generalizing patterns using part-of-speech information for the classification of lexical-semantic relation instances is analyzed. Results show that dependency information is decisive to achieve better results both in precision and recall, while generalizing features based on dependency information by replacing lexical forms with their part-of-speech increases the coverage of classification systems. Our experiments also make apparent that approaches based on the context where word pairs co-occur are upper-bound-limited by the times these appear in the same sentence. Therefore strategies to use information across sentence boundaries are necessary.
Anthology ID:
L14-1644
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
4308–4315
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/837_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Silvia Necşulescu, Sara Mendes, and Núria Bel. 2014. Combining dependency information and generalization in a pattern-based approach to the classification of lexical-semantic relation instances. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4308–4315, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
Combining dependency information and generalization in a pattern-based approach to the classification of lexical-semantic relation instances (Necşulescu et al., LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/837_Paper.pdf
PDF Search