Learning Recursive Segments for Discourse Parsing

Details Learning Recursive Segments for Discourse Parsing Learning Recursive Segments for Discourse Parsing

2010-03-28

arxiv.org/abs/1003.5372v1

Computer Science

Computation and Language

published at LREC 2010

Scientific paper

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 SDRT allows 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 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.

Affiliated with

Also associated with

No associations

Rating

Learning Recursive Segments for Discourse Parsing does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning Recursive Segments for Discourse Parsing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning Recursive Segments for Discourse Parsing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-127717