Algorithms for Generating Referring Expressions: Do They Do What People Do?

The natural language generation literature provides many algorithms for the generation of referring expressions. In this paper, we explore the question of whether these algorithms actually produce the kinds of expressions that people produce. We compare the output of three existing algorithms against a data set consisting of human-generated referring expressions, and identify a number of significant differences between what people do and what these algorithms do. On the basis of these observations, we suggest some ways forward that attempt to address these differences.

[1]  Terry Winograd,et al.  Understanding natural language , 1974 .

[2]  Emiel Krahmer,et al.  Efficient context-sensitive generation of referring expressions , 2002 .

[3]  Robert Dale,et al.  Cooking Up Referring Expressions , 1989, ACL.

[4]  David D. McDonald.  Natural language production as a process of decision-making under constraints , 1980 .

[5]  Kees van Deemter.  Generating Referring Expressions: Boolean Extensions of the Incremental Algorithm , 2002, CL.

[6]  Emiel Krahmer,et al.  Evaluating Multimodal NLG Using Production Experiments , 2004, LREC.

[7]  Kees van Deemter,et al.  Logical Form Equivalence: the Case of Referring Expressions Generation , 2001, EWNLG@ACL.

[8]  John A. Bateman,et al.  Using aggregation for selecting content when generating referring expressions , 1999, ACL.

[9]  Susan Sonnenschein,et al.  The development of referential communication skills: Some situations in which speakers give redundant messages , 1985 .

[10]  Takenobu Tokunaga,et al.  Generating Referring Expressions Using Perceptual Groups , 2004, INLG.

[11]  Eleanor Rosch,et al.  Principles of Categorization , 1978 .

[12]  T. Pechmann.  Incremental speech production and referential overspecification , 1989 .

[13]  D. Olson,et al.  The elaboration of the noun phrase in children's description of objects , 1975 .

[14]  Douglas Edmund Appelt,et al.  Planning natural language utterances to satisfy multiple goals , 1981 .

[15]  Emiel Krahmer,et al.  Graph-Based Generation of Referring Expressions , 2003, CL.

[16]  Matthew Stone,et al.  On identifying sets , 2000, INLG.

[17]  Albert Gatt,et al.  Structuring Knowledge for Reference Generation: a Clustering Algorithm , 2022 .

[18]  Robert Dale,et al.  A Fast Algorithm for the Generation of Referring Expressions , 1992, COLING.

[19]  Claire Gardent,et al.  Generating Minimal Definite Descriptions , 2002, ACL.

[20]  Helmut Horacek,et al.  An Algorithm for Generating Referential Descriptions with Flexible Interfaces , 1997, ACL.

[21]  J. Carletta,et al.  Risk-taking and recovery in task-oriented dialogue , 1996 .

[22]  Siobhan Chapman.  Logic and Conversation , 2005 .

[23]  Robert Dale,et al.  Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions , 1995, Cogn. Sci..

[24]  Robert Dale,et al.  Generating Referring Expressions Involving Relations , 1991, EACL.