Hybrid language processing in the Spoken Language Translator
| dc.creator | Rayner, Manny | |
| dc.creator | Carter, David | |
| dc.date | 1997-01-02 | |
| dc.date.accessioned | 2026-07-07T09:10:42Z | |
| dc.date.available | 2026-07-07T09:10:42Z | |
| dc.description | The paper presents an overview of the Spoken Language Translator (SLT) system's hybrid language-processing architecture, focussing on the way in which rule-based and statistical methods are combined to achieve robust and efficient performance within a linguistically motivated framework. In general, we argue that rules are desirable in order to encode domain-independent linguistic constraints and achieve high-quality grammatical output, while corpus-derived statistics are needed if systems are to be efficient and robust; further, that hybrid architectures are superior from the point of view of portability to architectures which only make use of one type of information. We address the topics of ``multi-engine'' strategies for robust translation; robust bottom-up parsing using pruning and grammar specialization; rational development of linguistic rule-sets using balanced domain corpora; and efficient supervised training by interactive disambiguation. All work described is fully implemented in the current version of the SLT-2 system. | |
| dc.description | 4 pages, uses icassp97.sty; to appear in ICASSP-97; see http://www.cam.sri.com for related material | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9701002 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9701002 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/151424 | |
| dc.subject | Computation and Language | |
| dc.title | Hybrid language processing in the Spoken Language Translator | |
| dc.type | text |