Paper: The Surprising Variance in Shortest-Derivation Parsing

ACL ID P11-2127
Title The Surprising Variance in Shortest-Derivation Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

We investigate full-scale shortest-derivation parsing (SDP), wherein the parser selects an analysis built from the fewest number of train- ing fragments. Shortest derivation parsing exhibits an unusual range of behaviors. At one extreme, in the fully unpruned case, it is neither fast nor accurate. At the other ex- treme, when pruned with a coarse unlexical- ized PCFG, the shortest derivation criterion becomes both fast and surprisingly effective, rivaling more complex weighted-fragment ap- proaches. Our analysis includes an investi- gation of tie-breaking and associated dynamic programs. At its best, our parser achieves an accuracy of 87% F1 on the English WSJ task with minimal annotation, and 90% F1 with richer annotation.