444
Views
9
CrossRef citations to date
0
Altmetric
Original Articles

Generation of effective referring expressions in situated context

&
Pages 986-1001 | Received 14 Mar 2012, Accepted 14 Aug 2013, Published online: 14 Nov 2013
 

Abstract

In task-oriented communication, references often need to be effective in their distinctive function, that is, help the hearer identify the referent correctly and as effortlessly as possible. However, it can be challenging for computational or empirical studies to capture referential effectiveness. Empirical findings indicate that human-produced references are not always optimally effective, and that their effectiveness may depend on different aspects of the situational context that can evolve dynamically over the course of an interaction. On this basis, we propose a computational model of effective reference generation which distinguishes speaker behaviour according to its helpfulness to the hearer in a certain situation, and explicitly aims at modelling highly helpful speaker behaviour rather than speaker behaviour invariably. Our model, which extends the planning-based paradigm of sentence generation with a statistical account of effectiveness, can adapt to the situational context by making this distinction newly for each new reference. We find that the generated references resemble those of effective human speakers more closely than references of baseline models, and that they are resolved correctly more often than those of other models participating in a shared-task evaluation with human hearers. Finally, we argue that the model could serve as a methodological framework for computational and empirical research on referential effectiveness.

Acknowledgements

Part of this work has been presented at the 2011 European Workshop on Natural Language Generation (Garoufi & Koller, Citation2011a, Citation2011b); we are thankful to the workshop's participants for their feedback. We also thank Ivan Titov for fruitful discussions and Albert Gatt as well as our reviewers for their very helpful comments.

Notes

1. Though this corpus is written, for the sake of simplicity we use the terms “speaker” and “hearer” for both spoken and written language settings.

2. See also an interesting computational treatment of Clark and Wilkes-Gibbs’ collaborative reference model by Heeman and Hirst (Citation1995). This earlier computational model addresses reference generation using methods from automated planning, as we also do in this work.

3. The GIVE-2 corpus is freely available and viewable online at: http://www.give-challenge.org/research/page.php?id=give-2-corpus

4. Further information on the GIVE Challenge as well as evaluation results are available at: http://www.give-challenge.org/research

Additional information

Funding

Funding: The research reported of here was partly supported by the Collaborative Research Center “Information Structure: The Linguistic Means of Structuring Utterances, Sentences and Texts” [SFB 632] at the University of Potsdam.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.