Paper: The utility of parse-derived features for automatic discourse segmentation

ACL ID P07-1062
Title The utility of parse-derived features for automatic discourse segmentation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2007
Authors

We investigate different feature sets for performing automatic sentence-level dis- course segmentation within a general ma- chine learning approach, including features derived from either finite-state or context- free annotations. We achieve the best re- ported performance on this task, and demon- strate that our SPADE-inspired context-free features are critical to achieving this level of accuracy. This counters recent results sug- gesting that purely finite-state approaches can perform competitively.