Book contents
- Frontmatter
- Contents
- List of contributors
- 1 Introduction
- Part I Joint construction
- Part II Reference
- 5 Referability
- 6 Referring expression generation in interaction: A graph-based perspective
- Part III Handling uncertainty
- Part IV Engagement
- Part V Evaluation and shared tasks
- Author index
- Subject index
- References
5 - Referability
from Part II - Reference
Published online by Cambridge University Press: 05 July 2014
Book contents
- Frontmatter
- Contents
- List of contributors
- 1 Introduction
- Part I Joint construction
- Part II Reference
- 5 Referability
- 6 Referring expression generation in interaction: A graph-based perspective
- Part III Handling uncertainty
- Part IV Engagement
- Part V Evaluation and shared tasks
- Author index
- Subject index
- References
Summary
Introduction
A key task of almost any natural language generation (NLG) system is to refer to entities. Linguists and philosophers have a long tradition of theorizing about reference. In the words of the philosopher John Searle,
Any expression which serves to identify any thing, process, event, action, or any other kind of individual or particular I shall call a referring expression. Referring expressions point to particular things; they answer the questions Who?, What?, Which?
(Searle, 1969)Referring expression generation (REG, sometimes GRE) is the task of producing a (logical or natural language) description of a referent that allows the reader to identify it. In producing a referring expression, an NLG system can make use of any information that it can safely assume the hearer to possess, based on a model of the world and of the hearer's knowledge about the world (the knowledge base(KB)). Given a REG algorithm and a KB, the following questions can be asked:
How many entities is the algorithm able to identify? We will call this the expressive power of an algorithm. Loosely speaking, the more entities the algorithm is able to single out, the greater its expressive power.
How empirically adequate are the referring expressions generated by the algorithm? For example, how human-like are they – to what extent do they resemble the human-produced referring expressions in a corpus? How effective are they – to what extent do they enable a human recipient to identify the referent easily, quickly, and reliably?
- Type
- Chapter
- Information
- Natural Language Generation in Interactive Systems , pp. 95 - 125Publisher: Cambridge University PressPrint publication year: 2014
References
, , and (2008). Referring expressions as formulas of description logic. In Proceedings of the International Conference on Natural Language Generation (INLG), pages 42-49, Salt Fork, OH. Association for Computational Linguistics.Google Scholar
(1999). Using aggregation for selecting content when generating referring expressions. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 127-134, College Park, MD. Association for Computational Linguistics.Google Scholar
, , , and (2010). Generating referring expressions in context: The GREC task evaluation challenges. In and , editors, Empirical Methods in Natural Language Generation, pages 294-327. Springer, Berlin, Germany.Google Scholar
, , , and (2011). Natural discourse reference generation reduces cognitive load in spoken systems. Natural Language Engineering, 17(3):311-329.CrossRefGoogle ScholarPubMed
and van (2007). A conceptual graph approach to the generation of referring expressions. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 2456-2461, Hyderabad, India. International Joint Conference on Artificial Intelligence.Google Scholar
and (1991). Content determination in the generation of referring expressions. Computational Intelligence, 7(4):252-265.CrossRefGoogle Scholar
and (1995). Computational interpretation of the Gricean maxims in the generation of referring expressions. Cognitive Science, 19(2):233-263.CrossRefGoogle Scholar
(2002). Generating minimal definite descriptions. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 96-103, Philadelphia, PA. Association for Computational Linguistics.Google Scholar
and (2007). Generating bridging definite descriptions. In and , editors, Computing Meaning, volume 3, pages 369-396. Springer, Dordrecht, The Netherlands.Google Scholar
(2007). Generating Coherent References to Multiple Entities. PhD thesis, Department of Computing Science, University of Aberdeen.Google Scholar
and (2010). Introducing shared tasks to NLG: The TUNA shared task evaluation challenges. In and , editors, Empirical Methods in Natural Language Generation, pages 264-293. Springer, Berlin, Heidelberg.Google Scholar
and (2010). Preferences versus adaptation during referring expression generation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 55-59, Uppsala, Sweden. Association for Computational Linguistics.Google Scholar
and (2008). Adapting referring expressions to the task environment. In Proceedings of the Annual Conference of the Cognitive Science Society (CogSci), pages 2404-2409, Washington, DC. Cognitive Science Society.Google Scholar
, , and (2000). Pronominalization revisited. In Proceedings of the International Conference on Computational Linguistics (COLING), pages 306-312, Saarbrücken, Germany. International Committee on Computational Linguistics.Google Scholar
(1996). A new algorithm for generating referential descriptions. In Proceedings of the European Conference on Artificial Intelligence (ECAI), pages 577-581, Budapest, Hungary. John von Neumann Computer Society.Google Scholar
(2004). On referring to sets of objects naturally. In Proceedings of the International Conference on Natural Language Generation (INLG), pages 70-79, Brockenhurst, UK. Springer.Google Scholar
, , and (2006). The even more irresistible SROIQ. In Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning, pages 57-67, Lake District, UK. Principles of Knowledge Representation and Reasoning, Inc.Google Scholar
and (2000). Learning attribute selections for non-pronominal expressions. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 181-190, Hong Kong. Association for Computational Linguistics.Google Scholar
(2007). Constraints on multiple center-embedding of clauses. Journal of Linguistics, 43(2):365-392.CrossRefGoogle Scholar
, , and (2006). Incremental generation of spatial referring expressions in situated dialog. In Proceedings of the International Conference on Computational Linguistics and the Annual Meeting of the Association for Computational Linguistics (COLING-ACL), pages 745-752, Sydney, Australia. Association for Computational Linguistics.Google Scholar
, , and (2012). Managing ambiguity in reference generation: The role of surface structure. Topics in Cognitive Science, 4(2):211-231.CrossRefGoogle ScholarPubMed
and (2002). Eficient context-sensitive generation of referring expressions. In and , editors, Information Sharing: Reference and Presupposition in Language Generation and Interpretation, pages 223-264. CSLI Publications, Stanford, CA.Google Scholar
and van (2012). Computational generation of referring expressions: A survey. Computational Linguistics, 38(1):173-218.CrossRefGoogle Scholar
, , and (2003). Graph-based generation of referring expressions. Computational Linguistics, 29(1):53-72.CrossRefGoogle Scholar
(1997). Plurals and collectivity. In and , editors, Handbook of Logic and Language, pages 1009-1053. Elsevier, Amsterdam, The Netherlands.Google Scholar
(1986). Logic Design Principles with Emphasis on Testable Semicustom Circuits. Prentice-Hall, Upper Saddle River, NJ.Google Scholar
(1957). On a generalization of quantifiers. Fundamenta Mathematicae, 44:12-36.CrossRefGoogle Scholar
, , and (2007). Generating referring expressions: Making referents easy to identify. Computational Linguistics, 33(2):229-254.CrossRefGoogle Scholar
(1996). Using centering to relax Gricean informational constraints on discourse anaphoric noun phrases. Language and Speech, 39(2-3):229-264.CrossRefGoogle Scholar
, , and (2008). ‘Proximal’ and ‘distal’ in language and cognition: Evidence from deictic demonstratives in Dutch. Journal of Pragmatics, 40(4):694-718.CrossRefGoogle Scholar
(1990). The computational complexity of avoiding conversational implicatures. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 97-104, Pittsburgh, PA. Association for Computational Linguistics.Google Scholar
, , and (2010). Charting the potential of description logic for the generation of referring expressions. In Proceedings of the International Conference on Natural Language Generation (INLG), pages 115-124, Trim, Ireland. Association for Computational Linguistics.Google Scholar
and (1988). Multi-level plurals and distributivity. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 17-24, Buffalo, NY. Association for Computational Linguistics.Google Scholar
(1969). Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press, Cambridge, UK.CrossRefGoogle Scholar
, , and (2009). Effective query rewriting with ontologies over DBoxes. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 923-925, Pasadena, CA. International Joint Conference on Artificial Intelligence.Google Scholar
and (2004). Generating referring expressions in open domains. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 407-414, Barcelona, Spain. Association for Computational Linguistics.Google Scholar
, , and (2011). Information status distinctions and referring expressions: An empirical study of references to people in news summaries. Computational Linguistics, 37(4):811-842.CrossRefGoogle Scholar
(2000). Towards a computational account of knowledge, action and inference in instructions. Journal of Language and Computation, 1(2):231-246.Google Scholar
(1984). Generalized quantifiers: Finite versus infinite. In and , editors, Generalized Quantifiers in Natural Language, pages 145-159. Foris Publications, Dordrecht, The Netherlands.Google Scholar
(2002). Generating referring expressions: Boolean extensions of the incremental algorithm. Computational Linguistics, 28(1):37-52.Google Scholar
, , , and (2012). Generation of referring expressions: Assessing the Incremental Algorithm. Cognitive Science, 36(5):799-836.Google ScholarPubMed
and (2001). Logical form equivalence: The case of referring expressions generation. In Proceedings of the European Workshop on Natural Language Generation (EWNLG), pages 21-28, Toulouse, France. Association for Computational Linguistics.Google Scholar
and (2007). Graphs and booleans: On the generation of referring expressions. In and , editors, Computing Meaning, volume 3, pages 397-422. Springer, Dordrecht, The Netherlands.Google Scholar
and (2006). Algorithms for generating referring expressions: Do they do what people do? In Proceedings of the International Conference on Natural Language Generation (INLG), pages 63-72, Sydney, Australia. Association for Computational Linguistics.Google Scholar
and (2008). The use of spatial relations in referring expression generation. In Proceedings of the International Conference on Natural Language Generation (INLG), pages 59-67, Salt Fork, OH. Association for Computational Linguistics, Association for Computational Linguistics.Google Scholar