Naslov
Semantic Dependency Graph Parsing Using Tree Approximations

Autori
Agić, Željko ; Koller, Alexander ; Oepen, Stephan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 11th International Conference on Computational Semantics (IWCS 2015) / - London : Delhi : Association for Computational Linguistics (ACL), 2015, 217-227

ISBN
978-1-941643-33-4

Skup
The 11th International Conference on Computational Semantics (IWCS 2015)

Mjesto i datum
London, Ujedinjeno Kraljevstvo, 15.04.2015. - 17.04.2015

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
semantic parsing; tree approximations

Sažetak
In this contribution, we deal with graph parsing, i.e., mapping input strings to graph-structured output representations, using tree approximations. We experiment with the data from the SemEval 2014 Semantic Dependency Parsing (SDP) task. We define various tree approximation schemes for graphs, and make twofold use of them. First, we statically analyze the semantic dependency graphs, seeking to unscover which linguistic phenomena in particular require the additional annotation expressivity provided by moving from trees to graphs. We focus on undirected base cycles in the SDP graphs, and discover strong connections to grammatical control and coordination. Second, we make use of the approximations in a statistical parsing scenario. In it, we convert the training set graphs to dependency trees, and use the resulting treebanks to build standard dependency tree parsers. We perform lossy graph reconstructions on parser outputs, and evaluate our models as dependency graph parsers. Our system outperforms the baselines by a large margin, and evaluates as the best non-voting tree approximation–based parser on the SemEval 2014 data, scoring at just over 81% in labeled F1.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA