Unsupervised structured semantic inference for spoken dialog reservation tasks

Alejandra Lorenzo (1) , Lina M. Rojas-Barahona (1) , Christophe Cerisara (1)

1 SYNALP - Natural Language Processing : representations, inference and semantics

This work proposes a generative model to infer latent semantic structures on top of manual speech transcriptions in a spoken dialog reservation task. The proposed model is akin to a standard semantic role labeling system, except that it is unsupervised, it does not rely on any syntactic information and it exploits concepts derived from a domain-specific ontology. The semantic structure is obtained with un- supervised Bayesian inference, using the Metropolis-Hastings sampling algorithm. It is evaluated both in terms of attachment accuracy and purity-collocation for clustering, and compared with strong baselines on the French MEDIA spoken-dialog corpus.

Domaines: Traitement du texte et du document

Alejandra Lorenzo, Lina M. Rojas-Barahona, Christophe Cerisara. Unsupervised structured semantic inference for spoken dialog reservation tasks. SIGDIAL - 14th annual SIGdial Meeting on Discourse and Dialogue - 2013, Aug 2013, Metz, France. pp.12-20. ⟨hal-00911017⟩