Constrained decoding for text-level discourse parsing

Abstract : This paper presents a novel approach to document-based discourse analysis by performing a global A* search over the space of possible structures while optimizing a global criterion over the set of potential coherence relations. Existing approaches to discourse analysis have so far relied on greedy search strategies or restricted themselves to sentence-level discourse parsing. Another advantage of our approach, over other global alternatives (like Maximum Spanning Tree decoding algorithms), is its flexibility in being able to integrate constraints (including linguistically motivated ones like the Right Frontier Constraint). Finally, our paper provides the first discourse parsing system for French; our evaluation is carried out on the Annodis corpus. While using a lot less training data than earlier approaches than previous work on English, our system manages to achieve state-of-the-art results, with F1-scores of 66.2 and 46.8 when compared to unlabeled and labeled reference structures.
Complete list of metadatas

Cited literature [34 references]  Display  Hide  Download

https://hal.inria.fr/hal-00750611
Contributor : Pascal Denis <>
Submitted on : Monday, November 12, 2012 - 10:11:02 PM
Last modification on : Wednesday, December 4, 2019 - 1:42:13 PM
Long-term archiving on: Wednesday, February 13, 2013 - 3:42:09 AM

File

coling2012.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00750611, version 1

Citation

Philippe Muller, Stergos Afantenos, Pascal Denis, Nicholas Asher. Constrained decoding for text-level discourse parsing. COLING - 24th International Conference on Computational Linguistics, Dec 2012, Mumbai, India. ⟨hal-00750611⟩

Share

Metrics

Record views

955

Files downloads

456