Combining semantic and syntactic structure for language modeling
| dc.creator | Bod, Rens | |
| dc.date | 2001-10-24 | |
| dc.date.accessioned | 2026-07-07T03:17:50Z | |
| dc.date.available | 2026-07-07T03:17:50Z | |
| dc.description | Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between non-headwords. We show that non-headword dependencies contribute to significantly improved word error rate, and that a data-oriented parsing model trained on semantically and syntactically annotated data can exploit these dependencies. This paper also contains the first DOP model trained by means of a maximum likelihood reestimation procedure, which solves some of the theoretical shortcomings of previous DOP models. | |
| dc.description | 4 pages | |
| dc.identifier | https://arxiv.org/abs/cs/0110051 | |
| dc.identifier | http://arxiv.org/abs/cs/0110051 | |
| dc.identifier | Proceedings ICSLP'2000, Beijing, China | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/30875 | |
| dc.subject | Computation and Language | |
| dc.subject | I.2.7 | |
| dc.title | Combining semantic and syntactic structure for language modeling | |
| dc.type | text |