Automatic dialogue act recognition with syntactic features

Král, Pavel; Cerisara, Christophe

doi:10.1007/s10579-014-9263-6

Cited by 11 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work has investigated different machine learning techniques for DA classification such as Maximum entropy, DBN, HMM, and SVM (Ang et al, 2005;Ji and Bilmes, 2005;Venkataraman et al, 2003;Webb et al, 2005;Fernandez and Picard, 2002;Mast et al, 1996;Liu, 2006;Kral and Cerisara, 2014). Different features have been explored in these models, including lexical, syntactic features, prosodic cues, and speaker interactions.…”

Section: Related Workmentioning

confidence: 99%

Using Context Information for Dialog Act Classification in DNN Framework

Liu¹,

Han²,

Tan³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

140

View full text Add to dashboard Cite

Previous work on dialog act (DA) classification has investigated different methods, such as hidden Markov models, maximum entropy, conditional random fields, graphical models, and support vector machines. A few recent studies explored using deep learning neural networks for DA classification, however, it is not clear yet what is the best method for using dialog context or DA sequential information, and how much gain it brings. This paper proposes several ways of using context information for DA classification, all in the deep learning framework. The baseline system classifies each utterance using the convolutional neural networks (CNN). Our proposed methods include using hierarchical models (recurrent neural networks (RNN) or CNN) for DA sequence tagging where the bottom layer takes the sentence CNN representation as input, concatenating predictions from the previous utterances with the CNN vector for classification, and performing sequence decoding based on the predictions from the sentence CNN model. We conduct thorough experiments and comparisons on the Switchboard corpus, demonstrate that incorporating context information significantly improves DA classification, and show that we achieve new state-of-the-art performance for this task.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Context Information for Dialog Act Classification in DNN Framework

Liu¹,

Han²,

Tan³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

140

View full text Add to dashboard Cite

show abstract

“…Their approach gives 95.8% DA recognition accuracy on Czech train ticket reservation corpus with 4 DA classes. A recent work in the dialogue act recognition field [20] also successfully uses a set of syntactic features derived from a deep parse tree. The reported accuracy is 97.7% on the same corpus.…”

Section: Related Workmentioning

confidence: 99%

On the effects of using word2vec representations in neural networks for dialogue act recognition

Cerisara

Král

Lenc

2018

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings. This is surprising, given that both of these techniques have proven exceptionally good in most other language-related domains. We propose in this work a new deep neural network that explores recurrent models to capture word sequences within sentences, and further study the impact of pretrained word embeddings. We validate this model on three languages: English, French and Czech. The performance of the proposed approach is consistent across these languages and it is comparable to the state-of-the-art results in English. More importantly, we confirm that deep neural networks indeed outperform a Maximum Entropy classifier, which was expected. However, and this is more surprising, we also found that standard word2vec embeddings do not seem to bring valuable information for this task and the proposed model, whatever the size of the training corpus is. We thus further analyse the resulting embeddings and conclude that a possible explanation may be related to the mismatch between the type of lexical-semantic information captured by the word2vec embeddings, and the kind of relations

show abstract

“…A DA represents the communicative intent behind the speaker's intent in a two or multi-party conversation. Work in [3,4,5,6,7,8,9,10] used different techniques to classify the dialog acts in different settings such as text chats, meetings, etc. Identifying the conversation sentences into DAs provides a way to understand the discourse structure of the conversation.…”

Section: Related Workmentioning

confidence: 99%

Aspect Classification for Legal Depositions

Chakravarty¹,

Chekuri²,

Mehrotra³

et al. 2020

Preprint

View full text Add to dashboard Cite

Attorneys and others have a strong interest in having a digital library with suitable services (e.g., summarizing, searching, and browsing) to help them work with large corpora of legal depositions. Their needs often involve understanding the semantics of such documents. That depends in part on the role of the deponent, e.g., plaintiff, defendant, law enforcement personnel, expert, etc. In the case of tort litigation associated with property and casualty insurance claims, such as relating to an injury, it is important to know not only about liability, but also about events, accidents, physical conditions, and treatments.We hypothesize that a legal deposition consists of various aspects that are discussed as part of the deponent testimony. Accordingly, we developed an ontology of aspects in a legal deposition for accident and injury cases. Using that, we have developed a classifier that can identify portions of text for each of the aspects of interest. Doing so was complicated by the peculiarities of this genre, e.g., that deposition transcripts generally consist of data in the form of question-answer (QA) pairs. Accordingly, our automated system starts with pre-processing, and then transforms the QA pairs into a canonical form made up of declarative sentences. Classifying the declarative sentences that are generated, according to the aspect, can then help with downstream tasks such as summarization, segmentation, question-answering, and information retrieval.Our methods have achieved a classification F1 score of 0.83. Having the aspects classified with a good accuracy will help in choosing QA pairs that can be used as candidate summary sentences, and to generate an informative summary for legal professionals or insurance claim agents. Our methodology could be extended to legal depositions of other kinds, and to aid services like searching.

show abstract

Automatic dialogue act recognition with syntactic features

Cited by 11 publications

References 42 publications

Using Context Information for Dialog Act Classification in DNN Framework

Using Context Information for Dialog Act Classification in DNN Framework

On the effects of using word2vec representations in neural networks for dialogue act recognition

Aspect Classification for Legal Depositions

Contact Info

Product

Resources

About