Data processing: speech signal processing – linguistics – language – Linguistics – Translation machine
Reexamination Certificate
2007-09-04
2007-09-04
{hacek over (S)}mits, Talivaldis Ivars (Department: 2626)
Data processing: speech signal processing, linguistics, language
Linguistics
Translation machine
C704S009000
Reexamination Certificate
active
11152352
ABSTRACT:
A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.
REFERENCES:
patent: 4942526 (1990-07-01), Okajima et al.
patent: 5418717 (1995-05-01), Su et al.
patent: 5495413 (1996-02-01), Kutsumi et al.
patent: 5528491 (1996-06-01), Kuno et al.
patent: 5799269 (1998-08-01), Schabes et al.
patent: 5937385 (1999-08-01), Zadrozny et al.
patent: 5966691 (1999-10-01), Kibre et al.
patent: 6108619 (2000-08-01), Carter et al.
patent: 6169972 (2001-01-01), Kono et al.
patent: 6275791 (2001-08-01), Weise
patent: 6405162 (2002-06-01), Segond et al.
patent: 6684188 (2004-01-01), Mitchell et al.
patent: 6745161 (2004-06-01), Arnold et al.
Nicolov et al. Approximate Generation from Non-Hierarchical Representations, 1996, Proceedings of the 8th. International Workshop on Natural Language Generation , pp. 31-40. □□
Varges et al. Instance-Based Natural Language Generation, Jun. 2001, Second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies 2001, pp. 1-8.
Stuart M. Shieber, Gertjan van Noord, Robert C. Moore, Fernando C.N. Pereira. Semantic-head-driven generation.Computational linguistics, 16(1), pp. 30-42, Mar. 1990.
Günter Neumann, Gertjan van Noord. Reversibility and Self-Monitoring in Natural Language Generation. In: Tomek Strazalkowski (ed.)Reversible Grammar in Natural Language Processing, pp. 59-95. Kluwer Academic Publishers, 1994.
Irene Langkilde, Kevin Knight. Generation that Exploits Corpus-Based Statistical Knowledge. In:Proceedings of the 36thAnnual Meeting of the Associateion for Computational Linguistics and the 17thInternational Conference on Computational Linguistics(COLING-ACL ''98), pp. 704-710, Montreal, Quebec Canada, Aug. 1998.
Srinivas Bangalore, Owen Rambow. Exploiting a Probabilistic Hierarchical Model for Generation. In:Proceedings of the 18thInternational Conference on Computation Linguistics(COLING 2000), Saarbrücken, Germany, Aug. 2000.
Zadrozny et al., W., “The Compactness of Construction Grammars”, IBM Research Report RC 20003, pp. 1-10, May 15, 1995.
European Search Report from Application No. EP 02 01 6129.
Bangalore et al., S., “Corpus-Based Lexical Choice in Natural Language Generation”, retrieved from the internet on Oct. 20, 2005 at http://www.research.att.com/{srini/Papers/Generation/ac12000.ps>, Oct. 2000.
Aikawa et al., T., “Multilingual Sentence Generation”, retrieved from the internet Oct. 20, 2005 at http://acl.ldc.upenn.edu/W/W01/W01-0808.pdf>, Jan. 2001.
Langkilde, I., “Forest-Based Statistical Sentence Generation”, retrieved from the internet on Oct. 20, 2005 at http://www.isi.edu/licensed-sw/halogen/rankalg.ps>, Apr. 29, 2000.
Calcagno Michael V.
Humphreys Kevin W.
Weise David Neal
Shortledge Thomas E.
Veldhuis-Kroeze John D.
Westman Champlin & Kelly P.A.
{hacek over (S)}mits Talivaldis Ivars
LandOfFree
Statistically driven sentence realizing method and apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Statistically driven sentence realizing method and apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistically driven sentence realizing method and apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3798172