Paper: Exploiting Multi-Word Units in History-Based Probabilistic Generation

ACL ID D07-1028
Title Exploiting Multi-Word Units in History-Based Probabilistic Generation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
Authors

We present a simple history-based model for sentence generation from LFG f-structures, which improves on the accuracy of previous models by breaking down PCFG indepen- dence assumptions so that more f-structure conditioning context is used in the predic- tion of grammar rule expansions. In addi- tion, we present work on experiments with named entities and other multi-word units, showing a statistically significant improve- ment of generation accuracy.