Paper: Transforming trees into hedges and parsing with hedgebank grammars

ACL ID P14-2129
Title Transforming trees into hedges and parsing with hedgebank grammars
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Finite-state chunking and tagging meth- ods are very fast for annotating non- hierarchical syntactic information, and are often applied in applications that do not require full syntactic analyses. Scenar- ios such as incremental machine transla- tion may benefit from some degree of hier- archical syntactic analysis without requir- ing fully connected parses. We introduce hedge parsing as an approach to recover- ing constituents of length up to some max- imum span L. This approach improves ef- ficiency by bounding constituent size, and allows for efficient segmentation strategies prior to parsing. Unlike shallow parsing methods, hedge parsing yields internal hi- erarchical structure of phrases within its span bound. We present the approach and some initial experiments on different infer- en...