Abstract
In this paper, we reflect on what we can learn about the processes involved in the generation of referring expressions by looking at a corpus of human-produced data. We find that the data vastly underspecifies what might be involved algorithmically, but it does rule out a number of popular algorithms for referring expression generation as candidates for models of what people do. We posit an alternative algorithmic schema which forces us to focus more clearly on the questions that need to be answered experimentally if we are to develop algorithms that emulate human behaviour on this task.
| Original language | English |
|---|---|
| Title of host publication | Pre-Cogsci 2009 |
| Subtitle of host publication | Production of referring expressions : bridging the gap between computational and empirical approaches to reference. Workshop program & proceedings |
| Place of Publication | Amsterdam |
| Publisher | Netherlands Organization for Scientific Research |
| Pages | 1-6 |
| Number of pages | 6 |
| Publication status | Published - 2009 |
| Event | Pre-Cogsci 2009 : Production of referring expressions : bridging the gap between computational and empirical approaches to reference - Amsterdam, The Netherlands Duration: 29 Jul 2009 → 29 Jul 2009 |
Conference
| Conference | Pre-Cogsci 2009 : Production of referring expressions : bridging the gap between computational and empirical approaches to reference |
|---|---|
| City | Amsterdam, The Netherlands |
| Period | 29/07/09 → 29/07/09 |