Abstract
We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.
Original language | English |
---|---|
Title of host publication | CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task |
Pages | 79-84 |
Number of pages | 6 |
Publication status | Published - 1 Dec 2009 |
Externally published | Yes |
Event | 13th Conference on Computational Natural Language Learning, CoNLL 2009 - Boulder, CO, United States Duration: 4 Jun 2009 → 4 Jun 2009 |
Other
Other | 13th Conference on Computational Natural Language Learning, CoNLL 2009 |
---|---|
Country | United States |
City | Boulder, CO |
Period | 4/6/09 → 4/6/09 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Human-Computer Interaction
- Linguistics and Language
Cite this
A second-order Joint Eisner model for syntactic and semantic dependency parsing. / Lluís, Xavier; Bott, Stefan; Marques, Lluis.
CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task. 2009. p. 79-84.Research output: Chapter in Book/Report/Conference proceeding › Chapter
}
TY - CHAP
T1 - A second-order Joint Eisner model for syntactic and semantic dependency parsing
AU - Lluís, Xavier
AU - Bott, Stefan
AU - Marques, Lluis
PY - 2009/12/1
Y1 - 2009/12/1
N2 - We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.
AB - We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.
UR - http://www.scopus.com/inward/record.url?scp=80053417203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80053417203&partnerID=8YFLogxK
M3 - Chapter
AN - SCOPUS:80053417203
SP - 79
EP - 84
BT - CoNLL- 2009: Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task
ER -