Exploiting Multi-Word Units in History-Based Probabilistic Generation

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 independence assumptions so that more f-structure conditioning context is used in the prediction of grammar rule expansions. In addition, we present work on experiments with named entities and other multi-word units, showing a statistically significant improvement of generation accuracy. Tested on section 23 of the Penn Wall Street Journal Treebank, the techniques described in this paper improve BLEU scores from 66.52 to 68.82, and coverage from 98.18% to 99.96%.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Deirdre Hogan, Conor Cafferkey, Aoife Cahill, Josef van Genabith
• Keywords: EMNLP 2007, Grammar Rule Expansions, Natural Language Processing, PCFG Independence Assumptions, Simple History-based Model