skip to main content
Using argumentation to control lexical choice: a functional unification implementation
Publisher:
  • Columbia University
  • 2960 Broadway New York, NY
  • United States
Order Number:UMI Order No. GAX93-33756
Bibliometrics
Skip Abstract Section
Abstract

This thesis presents new surface generation techniques that improve on both aspects of surface generation: (1) lexical choice, which consists of choosing words and their associated syntactic structures and (2) syntactic realization, which consists of combining these partial structures into grammatical sentences. The thesis investigates the impact of the pragmatic situation on surface generation. Because surface generation depends directly on many aspects of the situation, these new techniques allow a purely conceptual input to be expressed by a greater variety of linguistic forms and with more sensitivity to pragmatic factors than was previously possible.

Specifically, this research focuses on the impact on lexical choice of one part of the pragmatic situation: the speaker's argumentative intent, i.e., the goal of the speaker to convince the hearer of a certain conclusion. The argumentative intent can be realized by a variety of evaluative expressions appearing at various ranks in the syntactic structure. This thesis describes the selection of four classes of evaluative expressions: judgment determiners (i.e., many), scalar adjectives (i.e., difficult), connotative verbs (i.e., require, enjoy) and argumentative connectives (i.e., but, so). These four classes were not addressed in previous generators.

The scFUF formalism is introduced in this thesis to address the issue of complex constraint interaction arising when performing lexical choice under pragmatic constraints. scFUF is derived from Functional Unification Grammars (scFUGs), a formalism previously used for syntactic realization only. scFUF extends scFUGs by providing new mechanisms for control, for expressing hierarchical relations and for using modular knowledge sources. These extensions make scFUF capable of handling lexical choice. In addition, this thesis describes the use of scFUF to develop scSURGE, one of the largest and most widely used syntactic realization grammar available.

Finally these new generation techniques are applied to the implementation of scADVISOR II, a question-answering system helping students to choose classes for a semester. In particular, scADVISOR II uses the increased expressive flexibility provided by these techniques to convince a student to choose different classes by presenting the same objective data, retrieved from an underlying knowledge base, in different linguistic forms using evaluative expressions.

Cited By

  1. HerváS R, Francisco V and GerváS P (2019). Assessing the influence of personal preferences on the choice of vocabulary for natural language generation, Information Processing and Management: an International Journal, 49:4, (817-832), Online publication date: 1-Jul-2013.
  2. Rishes E, Lukin S, Elson D and Walker M Generating Different Story Tellings from Semantic Representations of Narrative Proceedings of the 6th International Conference on Interactive Storytelling - Volume 8230, (192-204)
  3. Keshtkar F and Inkpen D A pattern-based model for generating text to express emotion Proceedings of the 4th international conference on Affective computing and intelligent interaction - Volume Part II, (11-21)
  4. ACM
    Macedo H (2010). Model driven development approach to natural language generation systems, ACM SIGSOFT Software Engineering Notes, 35:4, (1-7), Online publication date: 20-Jul-2010.
  5. Fonseca M, Junior L, Melo A and Macedo H Innovative approach for engineering NLG systems Proceedings of the 9th international conference on Computational linguistics and intelligent text processing, (478-487)
  6. ACM
    Young R and Riedl M Towards an architecture for intelligent control of narrative in interactive virtual worlds Proceedings of the 8th international conference on Intelligent user interfaces, (310-312)
  7. Channarukul S, McRoy S and Ali S JYAG & IDEY Eighteenth national conference on Artificial intelligence, (994-995)
  8. Callaway C and Lester J (2002). Narrative prose generation, Artificial Intelligence, 139:2, (213-252), Online publication date: 1-Aug-2002.
  9. ACM
    McRoy S, Channarukul S and Ali S (2001). Creating natural language ouput for real-time applications, intelligence, 12:2, (21-34), Online publication date: 1-Jun-2001.
  10. Oh A and Rudnicky A Stochastic language generation for spoken dialogue systems Proceedings of the 2000 ANLP/NAACL Workshop on Conversational systems - Volume 3, (27-32)
  11. Carenini G and Moore J A strategy for generating evaluative arguments Proceedings of the first international conference on Natural language generation - Volume 14, (47-54)
  12. Channarukul S, McRoy S and Ali S Enriching partially-specified representations for text realization using an attribute grammar Proceedings of the first international conference on Natural language generation - Volume 14, (163-170)
  13. Jing H, Netzer Y, Elhadad M and McKeown K Integrating a large-scale, reusable lexicon with a natural language generator Proceedings of the first international conference on Natural language generation - Volume 14, (209-216)
  14. McRoy S, Channarukul S and Ali S YAG Proceedings of the first international conference on Natural language generation - Volume 14, (264-267)
  15. ACM
    Branting L, Callaway C, Mott B and Lester J Integrating discourse and domain knowledge for document drafting Proceedings of the 7th international conference on Artificial intelligence and law, (214-220)
  16. Barzilay R, McKeown K and Elhadad M Information fusion in the context of multi-document summarization Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, (550-557)
  17. Hovy E and Lin C Automated text summarization and the SUMMARIST system Proceedings of a workshop on held at Baltimore, Maryland: October 13-15, 1998, (197-214)
  18. Pan S and McKeown K Learning intonation rules for Concept to Speech generation Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 2, (1003-1009)
  19. Shaw J Segregatory coordination and ellipsis in text generation Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 2, (1220-1226)
  20. Jing H and McKeown K Combining multiple, large-scale resources in a reusable lexicon for natural language generation Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, (607-613)
  21. Langkilde I and Knight K Generation that exploits corpus-based statistical knowledge Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, (704-710)
  22. Cicekli I and Korkmaz T Generation of simple Turkish sentences with systemic-functional grammar Proceedings of the Joint Conferences on New Methods in Language Processing and Computational Natural Language Learning, (165-173)
  23. Netzer Y and Elhadad M Generating determiners and quantifiers in Hebrew Proceedings of the Workshop on Computational Approaches to Semitic Languages, (89-96)
  24. ACM
    Kerpedjiev S, Carenini G, Roth S and Moore J Integrating planning and task-based design for multimedia presentation Proceedings of the 2nd international conference on Intelligent user interfaces, (145-152)
  25. ACM
    Dalal M, Feiner S, McKeown K, Pan S, Zhou M, Höllerer T, Shaw J, Feng Y and Fromer J Negotiation for automated generation of temporal multimedia presentations Proceedings of the fourth ACM international conference on Multimedia, (55-64)
  26. ACM
    Walker M, Cahn J and Whittaker S Improvising linguistic style Proceedings of the first international conference on Autonomous agents, (96-105)
  27. Radev D and McKeown K Building a generation knowledge source using Internet-accessible newswire Proceedings of the fifth conference on Applied natural language processing, (221-228)
  28. McKeown K, Pan S, Shaw J, Jordan D and Allen B Language generation for multimedia healthcare briefings Proceedings of the fifth conference on Applied natural language processing, (277-282)
  29. Edmonds P Choosing the word most typical in context using a lexical co-occurrence network Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics, (507-509)
  30. Spyns P, Deprez F, Van Tichelen L and Van Coile B A practical message-to-speech strategy for dialogue systems Interactive Spoken Dialog Systems on Bringing Speech and NLP Together in Real Applications, (41-44)
  31. Lester J and Porter B (1997). Developing and empirically evaluating robust explanation generators, Computational Linguistics, 23:1, (65-101), Online publication date: 1-Mar-1997.
  32. Elhadad M, Robin J and McKeown K (1997). Floating constraints in lexical choice, Computational Linguistics, 23:2, (195-239), Online publication date: 1-Jun-1997.
  33. ACM
    McKeown K and Radev D Generating summaries of multiple news articles Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval, (74-82)
  34. Knight K and Hatzivassiloglou V Two-level, many-paths generation Proceedings of the 33rd annual meeting on Association for Computational Linguistics, (252-260)
  35. McKeown K, Kukich K and Shaw J Practical issues in automatic documentation generation Proceedings of the fourth conference on Applied natural language processing, (7-14)
  36. Reiter E Has a consensus NL generation architecture appeared, and is it psycholinguistically plausible? Proceedings of the Seventh International Workshop on Natural Language Generation, (163-170)
  37. Hatzivassiloglou V and McKeown K Towards the automatic identification of adjectival scales Proceedings of the 31st annual meeting on Association for Computational Linguistics, (172-182)
  38. McKeown K, Robin J and Tanenblatt M Tailoring lexical choice to the user's vocabulary in multimedia explanation generation Proceedings of the 31st annual meeting on Association for Computational Linguistics, (226-234)
  39. Elhadad M Generating coherent argumentative paragraphs Proceedings of the 14th conference on Computational linguistics - Volume 2, (638-644)
Contributors
  • Ben-Gurion University of the Negev

Index Terms

  1. Using argumentation to control lexical choice: a functional unification implementation

    Recommendations