Method and apparatus for recognizing multiword expressions

Details Method and apparatus for recognizing multiword expressions Method and apparatus for recognizing multiword expressions

2002-12-13

2008-03-18

Edouard, Patrick N. (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S251000, C704S254000, C704S009000

Reexamination Certificate

active

07346511

ABSTRACT:
Words of an input string are morphologically analyzed to identify their alternative base forms and parts of speech. The analyzed words of the input string are used to compile the input string into a first finite-state network. The first finite-state network is matched with a second finite-state network of multiword expressions to identify all subpaths of the first finite-state network that match one or more complete paths in the second finite-state network. Each matching subpath of the first finite-state network and path of the second finite-state network identify a multiword expression in the input string. The morphological analysis is performed without disambiguating words and without segmenting the input string into sentences in the input string to compile the first finite-state network with at least one path that identifies alternative base forms or parts of speech of a word in the input string.

REFERENCES:
patent: 4555796 (1985-11-01), Sakoe
patent: 5642522 (1997-06-01), Zaenen et al.
patent: 5644774 (1997-07-01), Fukumochi et al.
patent: 5696962 (1997-12-01), Kupiec
patent: 5819260 (1998-10-01), Lu et al.
patent: 5845306 (1998-12-01), Schabes et al.
patent: 5950184 (1999-09-01), Karttunen
patent: 6073098 (2000-06-01), Buchsbaum et al.
patent: 6243679 (2001-06-01), Mohri et al.
patent: 6321372 (2001-11-01), Poirier et al.
patent: 6393389 (2002-05-01), Chanod et al.
patent: 6505157 (2003-01-01), Elworthy
patent: 6629066 (2003-09-01), Jackson et al.
Mohri, Mehryar “Finite-State transducers in Language and Speech Processing”, 1997, Association for Computational Linguistics, AT&T Labs-Research, 42 pages.
Roche, Emmanuel, “Factorization of Finite-State Transducers”, Feb. 1995, Mitsubishi Electric Research Laboratories, 13 pages+ Abstract.
Bauer et al., “LOCOLEX: the translation rolls off your tongue”, Proceedings of ACH-ALLC, Santa-Barbara, USA, 1995.
Breidt et al., “Formal description of Multi-word Lexemes with the Finite State formalism: IDAREX”, Proceedings of COLING, Copenhagen, Danmark, 1996.
Chanod et al., “A Non-Deterministic Tokeniser for Finite-State Parsing”, Proc. ECAI '96 workshop on ‘Extended finite state models of language’ Budapest, 1996.
Karttunen, “Constructing lexical transducers”, published in Proceedings of COLING-94, 1:406-411, Kyoto, Japan, 1994.
Lucchesi, et al., “Applications of finite automata representing large vocabularies”, Software-Practice and Experience, vol. 23(1):15-30, 1993.
Segond et al., “Using a finite-state based formalism to identify and generate multiword expressions”, Technical report MLTT-019, Rank Xerox Research Centre, Grenoble, 1995.
Segond et al., “IDAREX: formal description of German and French Multi-Word Expressions with Finite-State Technology”, MLTT-022, Nov. 1995.
Silberztein, “INTEX: a corpus processing system”, Proceedings of COLING-94, vol. 1, Kyoto, Japan, 1994.
Silberztein, “INTEX”, (English Translation: Jordan Greenwood, Edition: Cederick Fairon) available on the Internet at http://grelis.univ-fcomte.fr/intex/downloads/Manual.pdf, 2001.
Silberztein, “INTEX and the processing of natural languages”, available on the Internet at http://grelis.univ-fcomte.fr/intex/downloads/Notes.pdf.
Woods, “Transition Network Grammars of Natural Language Analysis”, in Communications of the ACM, 13, 591-606, 1970. (Reprinted in Grosz B.J., K. S. Jones and B.L. Webber (eds.) Readings in Natural Language Processing. Los Altos, USA: Morgan Kaufmann, 1986, pp.71-87).
“XeLDA Overview” Xerox XeLDA® the linguistic engine, Jun. 2002.
“XeLDA C++API Programmer's Guide”, Xerox XeLDA® the linguistic engine, Jun. 2002.
U.S. Appl. No. 10/216,915 entitled “Information Retrieval And Encoding Via Substring-Number Mapping”.

Affiliated with

Also associated with

Rating

Method and apparatus for recognizing multiword expressions does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for recognizing multiword expressions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for recognizing multiword expressions will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3976003