SciDok

Eingang zum Volltext in SciDok

Lizenz

Report (Bericht) zugänglich unter
URN: urn:nbn:de:bsz:291-scidok-37668
URL: http://scidok.sulb.uni-saarland.de/volltexte/2011/3766/


Interleaving natural language parsing and generation through uniform processing

Neumann, Günter

Quelle: (1996) Kaiserslautern ; Saarbrücken : DFKI, 1996
pdf-Format:
Dokument 1.pdf (580 KB)

Bookmark bei Connotea Bookmark bei del.icio.us
SWD-Schlagwörter: Künstliche Intelligenz
Institut: DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
DDC-Sachgruppe: Informatik
Dokumentart: Report (Bericht)
Schriftenreihe: Research report / Deutsches Forschungszentrum für Künstliche Intelligenz [ISSN 0946-008x]
Bandnummer: 96-03
Sprache: Englisch
Erstellungsjahr: 1996
Publikationsdatum: 01.07.2011
Kurzfassung auf Englisch: We present a new model of natural language processing in which natural language parsing and generation are strongly interleaved tasks. Interleaving of parsing and generation is important if we assume that natural language understanding and production are not only performed in isolation but also can work together to obtain subsentential interactions in text revision or dialog systems. The core of the model is a new uniform agenda-driven tabular algorithm, called UTA. Although uniformly defined, UTA is able to configure itself dynamically for either parsing or generation, because it is fully driven by the structure of the actual input - a string for parsing and a semantic expression for generation. Efficient interleaving of parsing and generation is obtained through item sharing between parsing and generation. This novel processing strategy facilitates exchanging items (i.e., partial results) computed in one direction automatically to the other direction as well. The advantage of UTA in combination with the item sharing method is that we are able to extend the use of memorization techniques even to the case of an interleaved approach. In order to demonstrate UTA's utility for developing high-level performance methods, we present a new algorithm for incremental self-monitoring during natural language production.
Lizenz: Standard-Veröffentlichungsvertrag

Home | Impressum | Über SciDok | Policy | Kontakt | Datenschutzerklärung | English