论文信息 - Classifying dialog acts in human-human and human-machine spoken conversations

Classifying dialog acts in human-human and human-machine spoken conversations

Dialog acts represent the illocutionary aspect of the communication; depending on the nature of the dialog and its participants, different types of dialog act occur and an accurate classification of these is essential to support the understanding of human conversations. We learn effective discriminative dialog act classifiers by studying the most predictive classification features on Human-Human and Human-Machine corpora such as LUNA and SWITCHBOARD; additionally, we assess classifier robustness to speech errors. Our results exceed the state of the art on dialog act classification from reference transcriptions on SWITCHBOARD and allow us to reach a very satisfying performance on ASR transcriptions.

Giuseppe Riccardi | Silvia Quarteroni | G. Riccardi | S. Quarteroni

[1] Mark G. Core,et al. Coding Dialogs with the DAMSL Annotation Scheme , 1997 .

[2] Yorick Wilks,et al. Dialogue Act Classification Based on Intra-Utterance Features∗ , 2005 .

[3] Rosalind W. Picard,et al. Dialog Act Classification from Prosodic Features Using Support Vector Machines , 2002 .

[4] Roberto Basili,et al. Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification , 2007, ACL.

[5] Andreas Stolcke,et al. Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000, CL.

[6] Alessandro Moschitti,et al. Annotating Spoken Dialogs: From Speech Segments to Dialog Acts and Frame Semantics , 2009 .

[7] Hiyan Alshawi,et al. Effective Utterance Classification with Unsupervised Phonotactic Models , 2003, NAACL.

[8] Dirk Heylen,et al. DIALOGUE-ACT TAGGING USING SMART FEATURE SELECTION; RESULTS ON MULTIPLE CORPORA , 2006, 2006 IEEE Spoken Language Technology Workshop.