Paper: High Performance Segmentation Of Spontaneous Speech Using Part Of Speech And Trigger Word Information

ACL ID A97-1003
Title High Performance Segmentation Of Spontaneous Speech Using Part Of Speech And Trigger Word Information
Venue Applied Natural Language Processing Conference
Session Main Conference
Year 1997
Authors

We describe and experimentally evaluate an efficient method for automatically de- termining small clause boundaries in spon- taneous speech. Our method applies an ar- tificial neural network to information about part of speech and trigger words. We find that with a limited amount of data (less than 2500 words for the training set), a small sliding context window (+/-3 to- kens) and only two hidden units, the neural net performs extremely well on this task: less than 5% error rate and F-score (com- bined precision and recall) of over.85 on unseen data. These results prove to be better than those reported earlier using different approaches.