Sciweavers

Share
ICASSP
2009
IEEE

Spoken language interpretation: On the use of dynamic Bayesian networks for semantic composition

8 years 10 months ago
Spoken language interpretation: On the use of dynamic Bayesian networks for semantic composition
In the context of spoken language interpretation, this paper introduces a stochastic approach to infer and compose semantic structures. Semantic frame structures are directly derived from word and basic concept sequences representing the users' utterances. A rulebased process provides a reference frame annotation of the speech training data. Then dynamic Bayesian networks are used to hypothesize frames from test data. The semantic frames used in this work are specialized on the task domain from the Berkeley FrameNet set. Experiments are reported on the French MEDIA dialog corpus. For all the data, the manual transcriptions and annotations at the word and concept levels are available. Tests are performed under 3 different conditions raising in difficulty wrt the errors in the word and concept sequence inputs. Three different stochastic models are compared and the results confirm the ability of the proposed probabilistic frameworks to carry out a reliable semantic frame annotation....
Marie-Jean Meurs, Fabrice Lefevre, Renato de Mori
Added 18 Feb 2011
Updated 18 Feb 2011
Type Journal
Year 2009
Where ICASSP
Authors Marie-Jean Meurs, Fabrice Lefevre, Renato de Mori
Comments (0)
books