Learning Recursive Segments for Discourse Parsing
Stergos Afantenos, Pascal Denis, Philippe Muller, Laurence Danlos
Abstract
Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document always form a linear sequence (i.e., they can never be nested). Unfortunately, this assumption turns out to be too strong, for some theories of discourse, like the ""Segmented Discourse Representation Theory"" or SDRT, allow for nested discourse units. In this paper, we present a simple approach to discourse segmentation that is able to produce nested EDUs. Our approach builds on standard multi-class classification techniques making use of a regularized maximum entropy model, combined with a simple repairing heuristic that enforces global coherence. Our system was developed and evaluated on the first round of annotations provided by the French Annodis project (an ongoing effort to create a discourse bank for French). Cross-validated on only 47 documents (1,445 EDUs), our system achieves encouraging performance results with an F-score of 73% for finding EDUs.- Anthology ID:
- L10-1401
- Volume:
- Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
- Month:
- May
- Year:
- 2010
- Address:
- Valletta, Malta
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- Language:
- URL:
- http://www.lrec-conf.org/proceedings/lrec2010/pdf/582_Paper.pdf
- DOI:
- Cite (ACL):
- Stergos Afantenos, Pascal Denis, Philippe Muller, and Laurence Danlos. 2010. Learning Recursive Segments for Discourse Parsing. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).
- Cite (Informal):
- Learning Recursive Segments for Discourse Parsing (Afantenos et al., LREC 2010)
- PDF:
- http://www.lrec-conf.org/proceedings/lrec2010/pdf/582_Paper.pdf