[PDF][PDF] A syntactic and lexical-based discourse segmenter
Proceedings of the ACL-IJCNLP 2009 conference short papers, 2009•aclanthology.org
We present a syntactic and lexically based discourse segmenter (SLSeg) that is designed to
avoid the common problem of over-segmenting text. Segmentation is the first step in a
discourse parser, a system that constructs discourse trees from elementary discourse units.
We compare SLSeg to a probabilistic segmenter, showing that a conservative approach
increases precision at the expense of recall, while retaining a high F-score across both
formal and informal texts.
avoid the common problem of over-segmenting text. Segmentation is the first step in a
discourse parser, a system that constructs discourse trees from elementary discourse units.
We compare SLSeg to a probabilistic segmenter, showing that a conservative approach
increases precision at the expense of recall, while retaining a high F-score across both
formal and informal texts.
Abstract
We present a syntactic and lexically based discourse segmenter (SLSeg) that is designed to avoid the common problem of over-segmenting text. Segmentation is the first step in a discourse parser, a system that constructs discourse trees from elementary discourse units. We compare SLSeg to a probabilistic segmenter, showing that a conservative approach increases precision at the expense of recall, while retaining a high F-score across both formal and informal texts.
aclanthology.org
Showing the best result for this search. See all results