Dialog Act Modeling for Automatic Tagging and Recognition of Conversational Speech

By Andreas Stolcke, Klaus Ries, Noah B. Coccaro, Elizabeth Shriberg

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Improving Neural Language Models with a Continuous Cache (2016, background): “Language modeling is a core problem in natural language processing, with many applications such as machine translation (Brown et al., 1993), speech recognition (Bahl et al., 1983) or dialogue agents (Stolcke et al., 2000).”
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders (2017, background): “Thus, there has been a growing interest in applying encoder-decoder models (Sutskever et al., 2014) for modeling open-domain conversation (Vinyals and Le, 2015; Serban et al., 2016a).”
Synthesis Lectures on Human Language Technologies (2009, background): “Interpretation of dialogue acts is mainly modeled as a process of supervised classification in which classifiers are trained on a corpus of dialogues where each utterance is labeled with a dialogue act (see, e.g., Stolcke et al., 2000).”
Recurrent Convolutional Neural Networks for Discourse Compositionality (2013, methodology): “In addition, the recognition of dialogue acts within dialogues has largely been treated in non-compositional ways by way of language models coupled to hidden Markov sequence models (Stolcke et al., 2000).”
Algorithmic stemmers or morphological analysisq An evaluation (2009, background): “Just to cite a few papers: speaker recognition in telephone conversations (Przybocki and Martin, 1998), tagging dialogue acts in conversational speech (Stolcke et al., 2000), and managing discourse in spoken dialogue systems (Williams and Young, 2007).”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, methodology): “…effective for natural language processing, including tasks relevant to dialogue, such as dialogue act classification (Reithinger and Klesen, 1997; Stolcke et al., 2000), dialogue state tracking (Thomson and Young, 2010; Wang and Lemon, 2013; Ren et al., 2013; Henderson et al., 2013; Williams et…”
Enriching speech recognition with automatic detection of sentence boundaries and disfluencies (2006, background): “A general hidden Markov model (HMM) framework was designed to combine lexical and prosodic cues for tagging speech with various kinds of hidden structural information, including sentence boundaries [4], [16], punctuation marks [3], [17], disfluencies [18], topic boundaries [16], dialog acts [19], an”