The effect of syntactic representation on semantic role labeling

Richard Johansson, Pierre Nugues

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

227 Nedladdningar (Pure)

Sammanfattning

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.
Originalspråkengelska
Titel på värdpublikationProceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)
FörlagAssociation for Computational Linguistics
Sidor393-400
Antal sidor8
StatusPublished - 2008
EvenemangInternational Conference on Computational Linguistics (Coling) - Manchester
Varaktighet: 2008 aug. 182008 aug. 22

Konferens

KonferensInternational Conference on Computational Linguistics (Coling)
Period2008/08/182008/08/22

Ämnesklassifikation (UKÄ)

  • Datavetenskap (datalogi)

Fingeravtryck

Utforska forskningsämnen för ”The effect of syntactic representation on semantic role labeling”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här