International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 5, No. 8, 8 Jul. 2013
Cover page and Table of Contents: PDF (size: 402KB)
Managing Lexical Ambiguity in the Generation of Referring Expressions
Full Text (PDF, 402KB), PP.33-39
Views: 0 Downloads: 0
Author(s)
Index Terms
Natural Language Generation, Referring Expressions Generation, Lexical Ambiguity, Lexical Choice, Content Determination
Abstract
Most existing algorithms for the Generation of Referring Expressions (GRE) tend to produce distinguishing descriptions at the semantic level, disregarding the ways in which surface issues (e.g. linguistic ambiguity) can affect their quality. In this article, we highlight limitations in an existing GRE algorithm that takes lexical ambiguity into account, and put forward some ideas to address those limitations. The proposed ideas are implemented in a GRE algorithm. We show that the revised algorithm successfully generates optimal referring expressions without greatly increasing the computational complexity of the (original) algorithm.
Cite This Paper
Imtiaz Hussain Khan, Muhammad Haleem, "Managing Lexical Ambiguity in the Generation of Referring Expressions", International Journal of Intelligent Systems and Applications(IJISA), vol.5, no.8, pp.33-39, 2013. DOI:10.5815/ijisa.2013.08.04
Reference
[1]Reiter, E. and Dale, R. “Building Natural Language Generation Systems”. Cambridge University Press, 2000.
[2]Dale, R. “Generating Referring Expressions: Building Descriptions in a Domain of Objects and Processes”. MIT Press, 1992.
[3]Stone, M. and Webber, B. “Textual economy through close coupling of syntax and semantics”. In Proceedings of the 9th International Workshop on Natural Language Generation (INLG’98), New Brunswick, New Jersey, 1998, pp. 178–187.
[4]Krahmer, E. and Theune, M. “Efficient context-sensitive generation of referring expressions”. In van Deemter, K. and Kibble, R., editors, Information Sharing: Reference and Presupposition in Language Generation and Interpretation, Center for the Study of Language and Information (CSLI) Publications, 2002, pp. 223–264.
[5]Siddharthan, A. and Copestake, A. “Generating referring expressions in open domains”. In Proceedings of the 42nd Meeting of the Association for Computational Linguistics Annual Conference (ACL-04), Barcelona, Spain, 2004.
[6]Khan, I. H., van Deemter, K., and Ritchie, G. “Managing ambiguity in reference generation: the role of surface structure”. Topics in Cognitive Science, 2012, 4(2), pp. 211-31.
[7]Dale, R. and Reiter, E. “Computational interpretations of the Gricean maxims in the generation of referring expressions”. Cognitive Science, 1995, 18, pp. 233–263.
[8]Gardent, C. “Generating minimal definite descriptions”. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, USA, 2002.
[9]van Deemter, K. “Generating referring expressions: Boolean extensions of the incremental algorithm”. Computational Linguistics, 2004, 28(1), pp. 37–52.
[10]Horacek, H. “On referring to sets of objects naturally”. In Proceedings of the 3rd International Conference on Natural Language Generation (INLG’04), Brockenhurst England, 2004, pp 70–79.
[11]Krahmer, E., van Erk, S., and Verleg, A. “Graph-based generation of referring expressions”. Computational Linguistics, 2003, 29(1), pp. 53–72.
[12]Miller, G. “WordNet: a lexical database for English”. Communications of the Association for Computing Machinery (ACM), 1995, 38(11), pp. 39–41.
[13]Murphy, G. L. “Noun phrase interpretation and conceptual combination”. Journal of Memory and Language, 1990, 29(3), pp. 259–288.
[14]Lapata, M., Mcdonald, S., and Keller, F. “Determinants of adjective-noun plausibility”. In Proceedings of the 9th Conference of the European Chapter of the Association for Computational Linguistics (ACL), 1999, pp. 30–36.
[15]van Jaarsveld, H. and Dra, I. “Effects of collocational restrictions in the interpretation of adjective-noun combinations”. Journal of Language and Cognitive Processes, 2003, 18(1), pp. 47–60.
[16]Gatt, A. “Generating Coherent References to Multiple Entities”. An unpublished doctoral thesis, The University of Aberdeen, Aberdeen, Scotland, 2007.
[17]Wingfield, A. “Effects of frequency on identification”. American Journal of Psychology, 1968, 81, pp. 226–234.
[18] Borowsky, R. and Masson, M. E. “Semantic ambiguity effects in word identification”. Journal of Experimental Psychology: Learning Memory and Cognition, 1996, 22, pp. 63–85.
[19]Azuma, T. “Why safe is better than fast: The relatedness of a word’s meanings affects lexical decision times”. Journal of Memory and Language, 1997, 36(4), pp. 484–504.
[20]Rodd, J., Gaskell, G., and Marslen-Wilson,W. “The advantages and disadvantages of semantic ambiguity”. In Proceedings of the 22nd Annual Conference of the Cognitive Science Society, Mahwah, New Jersey, 2000, pp. 405–410.
[21]Huang, C.-R., Chen, C.-R., and Shen, C. C. “Quantitative criteria for computational Chinese, the nature of categorical ambiguity and its implications for language processing: A corpus-based study of mandarin Chinese”. In Nakayama, M., editor, Sentence Processing in East Asian Languages, Stanford: Center for the Study of Language and Information (CSLI) Publications, 2002, pp. 53–83.
[22]Stone, M. “On identifying sets”. In Proceedings of the 1st International Conference on Natural Language Generation (INLG’00), pp. 116–123, 2000, Mitzpe Ramon.
[23]van Deemter, K. and Krahmer, E. Graphs and Booleans: On the generation of referring expressions. In H. Bunt and R. Muskens, editors, Computing Meaning, Vol. III, Studies in Linguistics and Philosophy. Dordrecht: Kluwer, 2006.