Paper: Early Deletion Of Fillers In Processing Conversational Speech

ACL ID N06-2019
Title Early Deletion Of Fillers In Processing Conversational Speech
Venue Human Language Technologies
Session Short Paper
Year 2006
Authors

This paper evaluates the benefit of deleting fillers (e.g. you know, like) early in parsing conver- sational speech. Readability studies have shown that disfluencies (fillers and speech repairs) may be deleted from transcripts without compromising meaning (Jones et al. , 2003), and deleting repairs prior to parsing has been shown to improve its accuracy (Charniak and Johnson, 2001). We ex- plore whether this strategy of early deletion is also beneficial with regard to fillers. Reported exper- iments measure the effect of early deletion under in-domain and out-of-domain parser training con- ditions using a state-of-the-art parser (Charniak, 2000). While early deletion is found to yield only modest benefit for in-domain parsing, significant improvement is achieved for out-of-domain adap- tat...