Vorlesung: Suchverfahren in natürlichsprachlichen Systemen

Sommersemester 2009

Veranstalter: Helmut Horacek

Zeit und Ort: Di 12-14, Hörsaal 001, Geb. E13

Beginn: 21.4.

Ende (letzter Termin): 23.6.

2 Extra Termine: Fr 15.5. und 29.5., 12-14, Seminarraum 2, Geb. E2.5



Inhalt

Das Gebiet heuristische Suche bietet eine Reihe effizienter Suchverfahren an, deren Einsatz für verschiedene Bereiche der automatischen Sprachverarbeitung zielführend erscheint und auch versucht wurde. Ein Hauptproblem besteht dabei in der Diskrepanz zwischen der Erfordernis eines homogenen Suchraums von seiten der Suchverfahren und den zum Teil recht heterogenen sprachlichen Beschreibungen. In dieser Vorlesung werden Wege aufgezeigt, wie diese Diskrepanz durch geeignete Modellierung und Kompromisse in Systemarchitekturen überwunden werden kann. Dabei werde ich folgende Aspekte behandeln:


Folien

1. Introduction

2. Basic search techniques

3. Syntactic generation

4. Probabilistic syntactic analysis

5. Stochastic generation

6. Hunter Gatherer

7. Machine translation

8. Aggregation

9. Discourse Parsing

10. Dialog systems

11. Text planning architecture

12. Summary and References

Literatur

Einführung

Computerlinguistik und Sprachtechnologie. K.-U. Carstensen et al. (ed.), Spektrum Lehrbuch, 2001.

Speech and Language Processing. Jurafsky and Martin, Prentice Hall, 2000.

Referenzausdrücke

Robert Dale (1989). Cooking up referring expressions. Annual Meeting of the ACL Proceedings of the 27th annual meeting on Association for Computational Linguistics, pp. 68-75

Ehud Reiter (1990). The computational complexity of avoiding conversational implicatures Proceedings of the 28th annual meeting on Association for Computational Linguistics, pp. 97 - 104

Robert Dale and Nicholas Haddock (1991) Generating referring expressions involving relations Proceedings of the 1991 Meeting of the European Chapter of the Association for Computational Linguistics, pp. 161-166

R. Dale, E. Reiter. Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions. Cognitive Science 18, pp. 233-263, 1995.

C. Gardent. Generating Minimal Definite Descriptions. In Proc. of ACL-2002, pp. 96-103, 2002.

K. van Deemter. Generating Referring Expressions: Boolean Extensions of the Incremental Algorithm. Computational Linguistics, 28(1), pp. 37-52, 2002.

H. Horacek. A Best-First Search Algorithm for Generating Referring Expressions. In Proc. of EACL'2003, pp. 206-213, 2003.

Bernd Bohnet and Robert Dale. (2005) Viewing Referring Expression Generation as a Search Problem. Nineteenth International Joint Conference on Artifical Intelligence (IJCAI). Edinburgh.

Syntax analyse und -generierung

Collins, M. (2003). Head-driven statistical models for natural language parsing. Computational Linguistics, 29(4), 589--637.

Bernd Kiefer, Hans-Ulrich Krieger, John Carroll, and Rob Malouf. A Bag of Useful Techniques for Efficient and Robust Parsing Proceedings of the ACL-99: the 37th Annual Meeting of the Association for Computational Linguistics, University of Maryland, 1999.

Whitelock, Peter (1988): Shake-and-Bake Generation. In Proc. of COLING 88, Budapest.

Shieber, Stuart/Pereira, Fernando/van Noord, Gertjan/Moore, Robert (1990): Semantic-Head-Driven Generation. Computational Linguistics 16, 30-42.

Kay, Martin (1996): Chart Generation. In Proc. of ACL-96, Santa Cruz, CA, pp. 200-204.

Carroll, John/Copestake, Ann/Flickinger, Dan/Poznanski, Victor (1999): An Efficient Generator for (Semi-)Lexicalist Grammars. In Proc. of the 7th European Workshop on Natural Language Generation, Toulouse, France, pp. 86-95.

Michael White. Efficient Realization of Coordinate Structures in Combinatory Categorial Grammar. Research on Language and Computation, Volume 4, Number 1, June 2006, pp. 39-75

Maschinelle Übersetzung und Lexikalisierung

U. Germann, M. Jahr, K. Knight, D. Marcu, and K. Yamada (2001). Fast Decoding and Optimal Decoding for Machine Translation Proc. of the Conference of the Association for Computational Linguistics (ACL).

K. Yamada and K. Knight), 2002. A Decoder for Syntax-Based Statistical MT. Proc. of the Conference of the Association for Computational Linguistics (ACL).

Franz Josef Och, Nicola Ueffing, Hermann Ney (2001). An Efficient A* Search Algorithm for Statistical Machine Translation Data-Driven Machine Translation Workshop, pp. 55-62.

Beale, Stephen (1997): Hunter-Gatherer: Applying Constraint Satsifaction, Branch-and-Bound and Solution Synthesis to Computational Semantics. Ph. Dissertation, School of Computer Science, Carnegie-Mellon University.

Diskursinterpretation

Daniel Marcu. The Rhetorical Parsing of Unrestricted Texts: A Surface-Based Approach. Computational Linguistics, 26 (3), pages 395-448

Huong Thang Le, Geetha Abeysinghe, and Christian Huyck (2004). Generating Discourse Structures for Written Texts. Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004).

Generierung

Robin, Jacques/Mc Keown, Kathleen (1996): Empirically Designing and Evaluating a New Revision-Based Model for Summary Generation. Artificial Intelligence 85, Special Issue on Empirical Methods.

James Shaw. Segregatory Coordination and Ellipsis in Text Generation. In Proc. of the 36th Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, pages 1220-1226, Montreal, Canada

Helmut Horacek. Handling Dependencies in Reorganizing Content Specifications: A Case Study of Case Analysis Research on Language and Computation, Volume 4, Number 1, June 2006, pp. 111-139

Bemerkung

Gemeinsame Veranstaltung Informatik/Computerlinguistik

Schein

Mündliche Prüfung

Studienpunkte

Informatik 4, CL Diplom 2, CL Bachelor 3


E-mail Helmut Horacek