We are interested in the problem of discourse parsing of textual documents. We present a novel end-to-end discourse parser that, given a plain text document in input, identifies the discourse relations in the text, assigns them a semantic label and detects discourse arguments spans. The parsing architecture is based on a cascade of decisions supported by Conditional Random Fields (CRF). We train and evaluate three different parsers using the PDTB corpus. The three system versions are compared to evaluate their robustness with respect to deep/shallow and automatically extracted syntactic features.

End-to-End Discourse Parser Evaluation

Ghosh, Sucheta;Tonelli, Sara;Riccardi, Giuseppe;
2011-01-01

Abstract

We are interested in the problem of discourse parsing of textual documents. We present a novel end-to-end discourse parser that, given a plain text document in input, identifies the discourse relations in the text, assigns them a semantic label and detects discourse arguments spans. The parsing architecture is based on a cascade of decisions supported by Conditional Random Fields (CRF). We train and evaluate three different parsers using the PDTB corpus. The three system versions are compared to evaluate their robustness with respect to deep/shallow and automatically extracted syntactic features.
2011
Semantic Computing (ICSC), 2011 Fifth IEEE International Conference on
Palo Alto
IEEE
9781457716485
Ghosh, Sucheta; Tonelli, Sara; Riccardi, Giuseppe; R., Johansson
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/89858
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 87
social impact