[Ltg] LTG-Seminar [PRE-ALTA Presentations, Nov 29, E6A 357]

[Rolf Schwitter]

----
LTG Seminar
 - see: http://www.clt.mq.edu.au/Events/Seminars.html

Monday, November 29, 2004 at 11am
Macquarie Uni, E6A 357
----

Title: User Responses to Speech Recognition Errors: Consistency of Behaviour 
Across Domains
Speaker: Stephen Choularton

The problems caused by imperfect speech recognition in spoken dialogue 
systems are well known: they confound the ability of the system to manage 
the dialogue, and can lead to both user frustration and task failure. 
Speech recognition errors are likely to persist for the foreseeable future, 
and so the development and adoption of a well-founded approach to the 
handling of error situations may be an important component in achieving 
general public acceptability for systems of this kind.  In this paper, we 
compare two studies of user behaviour in response to speech recognition 
errors in quite different dialog applications; the analysis supports the 
view that user behaviour during error conditions contains a large component 
that is independent of the domain of the dialogue. The prospect of a 
consistent response to errors across a wide range of domains enhances the 
prospects for a general theory of error recognition and repair.

----

Title: Referring Expression Generation as a Search Problem
Speaker: Bernd Bohnet

One of the most widely explored issues in natural language generation is the 
generation of referring expressions (GRE): given an entity we want to refer 
to, how do we work out the content of a referring expression that uniquely 
identifies the intended referent? Over the last 15 years, a number of 
authors have proposed a wide range of algorithms for addressing different 
aspects of this problem, but the different approaches taken have made it 
very difficult to compare and contrast the algorithms provided in any 
meaningful way.  In this paper, we propose a characterisation of the problem 
of referring expression generation as a search problem; this allows us to 
recast existing algorithms in a way that makes their similarities and 
differences clear.


----

Title: Controlled Natural Language meets the Semantic Web
Speaker: Rolf Schwitter

In this talk I will present PENG-D, a proposal for a controlled natural 
language that can be used for expressing knowledge about resources in the 
Semantic Web and for specifying ontologies in a human-readable way. After a 
brief overview of the main Semantic Web enabling technologies (and their 
deficiencies), I will  show how statements and rules written in PENG-D are 
related to (a subset of) RDFS and OWL and how this knowledge can be 
translated into an expressive fragment  of first-order logic. The resulting 
information can then be further processed by  third-party reasoning services 
and queried in PENG-D.