Combining symbolic and corpus-based approaches for the generation of successful referring expressions

We present an approach to the generation of referring expressions (REs) which computes the unique RE that it predicts to be fastest for the hearer to resolve. The system operates by learning a maximum entropy model for referential success from a corpus and using the model's weights as costs in a metric planning problem. Our system outperforms the baselines both on predicted RE success and on similarity to human-produced successful REs. A task-based evaluation in the context of the GIVE-2.5 Challenge on Generating Instructions in Virtual Environments verifies the higher RE success scores of the system.

[1]  Matthew Stone,et al.  Microplanning with Communicative Intentions: The SPUD System , 2001, Comput. Intell..

[2]  Oliver Lemon,et al.  Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems , 2010, ACL.

[3]  Ielka van der Sluis,et al.  Evaluating algorithms for the Generation of Referring Expressions using a balanced corpus , 2007, ENLG.

[4]  Albert Gatt,et al.  Intrinsic vs. Extrinsic Evaluation Measures for Referring Expression Generation , 2008, ACL.

[5]  Johanna D. Moore,et al.  Report on the Second NLG Challenge on Generating Instructions in Virtual Environments (GIVE-2) , 2010, INLG.

[6]  Douglas E. Appelt,et al.  Planning English Sentences , 1988, Cogn. Sci..

[7]  Alexander Koller,et al.  The Potsdam NLG systems at the GIVE-2.5 Challenge , 2011, ENLG.

[8]  Johanna D. Moore,et al.  The First Challenge on Generating Instructions in Virtual Environments , 2010, Empirical Methods in Natural Language Generation.

[9]  Albert Gatt,et al.  Introducing Shared Tasks to NLG: The TUNA Shared Task Evaluation Challenges , 2010, Empirical Methods in Natural Language Generation.

[10]  Emiel Krahmer,et al.  Introducing shared task evaluation to NLG : The TUNA shared task evaluation challenges , 2010 .

[11]  Laura Stoia,et al.  Noun Phrase Generation for Situated Dialogs , 2006, INLG.

[12]  Jörg Hoffmann,et al.  Extending FF to Numerical State Variables , 2002, ECAI.

[13]  Mariët Theune,et al.  Report on the Second Second Challenge on Generating Instructions in Virtual Environments (GIVE-2.5) , 2011, ENLG.

[14]  Matthew Stone,et al.  Textual Economy Through Close Coupling of Syntax and Semantics , 1998, INLG.

[15]  Emiel Krahmer,et al.  Controlling Redundancy in Referring Expressions , 2008, LREC.

[16]  Aravind K. Joshi,et al.  Tree-Adjoining Grammars , 1997, Handbook of Formal Languages.

[17]  Alexander Koller,et al.  Automated Planning for Situated Natural Language Generation , 2010, ACL.

[18]  Matthew Stone,et al.  Sentence generation as a planning problem , 2007, ACL.

[19]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[20]  Alexander Koller,et al.  The GIVE-2 Corpus of Giving Instructions in Virtual Environments , 2010, LREC.

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

[22]  Maria Fox,et al.  PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains , 2003, J. Artif. Intell. Res..

[23]  Daniel Bauer,et al.  Sentence Generation as Planning with Probabilistic LTAG , 2010, TAG.

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

[25]  Robert Dale,et al.  The Use of Spatial Relations in Referring Expression Generation , 2008, INLG.

[26]  Nina Dethlefs,et al.  Optimising Natural Language Generation Decision Making For Situated Dialogue , 2011, SIGDIAL Conference.

[27]  Judith Masthoff,et al.  Generating Referring Expressions: Making Referents Easy to Identify , 2007, Computational Linguistics.

[28]  Albert Gatt,et al.  The attribute selection for GRE challenge: overview and evaluation results , 2007, MTSUMMIT.

[29]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[30]  Dan Klein,et al.  A Game-Theoretic Approach to Generating Spatial Descriptions , 2010, EMNLP.