Macquarie University, Sydney Macquarie University ResearchOnline

Showing items 1 - 13 of 13.

Add to Quick Collection   All 13 Results

  • First
  • Previous
  • 1
  • Next
  • Last
Sort:
 Add All Items to Quick Collection
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/161018
Description: The Big Australian Speech Corpus project incorporates the strategic goals of 30 Chief Investigators from various speech science areas. Speech from 1000 geographically and socially diverse speakers is ... More
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/159169
Description: Traditional computational approaches to referring expression generation operate in a deliberate manner, choosing the attributes to be included on the basis of their ability to distinguish the intended ... More
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/160931
Description: Recent years have seen a trend towards empirically motivated and more data-driven approaches in the field of referring expression generation (REG). Much of this work has focussed on initial reference ... More
Full Text: Full Text
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/160997
Description: A key characteristic of many existing referring expression generation (REG) algorithms is serial dependency: attributes are selected for inclusion one at a time, and the decision to include each attri ... More
Full Text: Full Text
Reviewed: Reviewed
Date: 2011
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/160927
Description: Traditional approaches to referring expression generation (REG) have taken as a fundamental requirement the need to distinguish the intended referent from other entities in the context. It seems obvio ... More
Full Text: Full Text
Reviewed: Reviewed
Date: 2010
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/323533
Description: A central purpose of referring expressions is to distinguish intended referents from other entities that are in the context; but how is this context determined? This paper draws a distinction between ... More
Reviewed: Reviewed
Date: 2010
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/323629
Description: In this paper we describe machine learning experiments that aim to characterise the content selection process for distinguishing descriptions. Our experiments are based on two large corpora of human-p ... More
Reviewed: Reviewed
Date: 2009
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/347058
Description: 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 under ... More
Reviewed: Reviewed
Date: 2009
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/154894
Description: In this paper, we explore a corpus of human-produced referring expressions to see to what extent we can learn the referential behaviour the corpus represents. Despite a wide variation in the way subje ... More
Reviewed: Reviewed
Date: 2008
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/165910
Description: When we describe an object in order to enable a listener to identify it, we often do so by indicating the location of that object with respect to other objects in a scene. This requires the use of a r ... More
Reviewed: Reviewed
Date: 2008
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/155805
Description: There is a prevailing assumption in the literature on referring expression generation that relations are used in descriptions only ‘as a last resort’, typically on the basis that including the second ... More
Reviewed: Reviewed
Date: 2007
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/153211
Description: Almost all existing referring expression generation algorithms aim to find one best referring expression for a given intended referent. However, human-produced data demonstrates that, for any given en ... More
Reviewed: Reviewed
Date: 2006
Language: eng
Resource Type: conference paper
Identifier: http://hdl.handle.net/1959.14/102703
Description: 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 ... More
Reviewed: Reviewed
  • First
  • Previous
  • 1
  • Next
  • Last