Summary of the paper
| Title | Dialogue Reference in a Visual Domain |
|---|---|
| Authors | Jette Viethen, Simon Zwarts, Robert Dale and Markus Guhe |
| Abstract | A central purpose of referring expressions is to distinguish intended referentsfrom other entities that are in the context; but how is this contextdetermined? This paper draws a distinction between discourse context ―otherentities that have been mentioned in the dialogue― and visual context―visually available objects near the intended referent. It explores how thesetwo different aspects of context have an impact on subsequent reference in adialogic situation where the speakers share both discourse and visual context.In addition we take into account the impact of the reference history ―formsof reference used previously in the discourse― on forming what have beencalled conceptual pacts. By comparing the output of different parametersettings in our model to a data set of human-produced referring expressions, wedetermine that an approach to subsequent reference based on conceptual pactsprovides a better explanation of our data than previously proposed algorithmicapproaches which compute a new distinguishing description for the intendedreferent every time it is mentioned. |
| Language | Anaphora, Coreference |
| Topics | Natural Language Generation, Dialogue, Anaphora, Coreference |
Full paper  |
Dialogue Reference in a Visual Domain |
| Bibtex | @InProceedings{VIETHEN10.578, author = {Jette Viethen, Simon Zwarts, Robert Dale and Markus Guhe}, title = {Dialogue Reference in a Visual Domain}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |