Unsegmented Dialogue Act Annotation and Decoding with N-Gram Transducers

Martínez-Hinarejos, Carlos D.; Benedí, José-Miguel; Tamarit, Vicent

doi:10.1109/taslp.2014.2377595

Cited by 5 publications

(8 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dialogue act recognition task is actually composed of two sub-tasks: one for dialogue act segmentation and another for dialogue act classification. For practical application of dialogue act recognition systems, it is essential to perform both tasks, either in cascade [2] or jointly by augmenting the DA labels with BIO-like (Begin-Inside-Out) prefixes [28], or with N-Gram transducers [27]. However, it is also a common practice to assume that segmentation is given and to only classify the given segments.…”

Section: Dialogue Act Recognitionmentioning

confidence: 99%

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

Cerisara

Král

Lenc

2018

Computer Speech & Language

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

Section: Dialogue Act Recognitionmentioning

confidence: 99%

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

Cerisara

Král

Lenc

2018

Computer Speech & Language

View full text Add to dashboard Cite

show abstract

“…However in the simple task, the accuracy of 0.720 repair onset prediction is respectable (comparable to (Georgila, 2009)), and is useful enough to allow realistic relative repair rates, in line with our motivation. The complex tagging system performs poorly on repairs compared to the literature, however the lack of segementation makes this a considerably harder task, in the same way as dialogue act tagging results are lower on unsegmented transcripts (Martínez-Hinarejos et al, 2015). Edit term detection performs very well at 0.918, approaching the state-of-the-art on Switchboard reported at 0.938 .…”

Section: Resultsmentioning

confidence: 88%

Joint, Incremental Disfluency Detection and Utterance Segmentation from Speech

Hough¹,

Schlangen²

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

We present the joint task of incremental disfluency detection and utterance segmentation and a simple deep learning system which performs it on transcripts and ASR results. We show how the constraints of the two tasks interact. Our joint-task system outperforms the equivalent individual task systems, provides competitive results and is suitable for future use in conversation agents in the psychiatric domain.

show abstract

“…The study using prosodic features focused on the prediction of the generic top level labels, while the study using textual features considered the combination of the multiple levels. Additionally, the latter study, as well as a more recent one [12], explored the recognition of dialog acts on unsegmented turns using n-gram transducers. However, in those cases, the focus was on the segmentation process.…”

Section: Related Workmentioning

confidence: 99%

End-to-End Multi-Level Dialog Act Recognition

Ribeiro¹,

Ribeiro²,

Matos³

2018

IberSPEECH 2018

View full text Add to dashboard Cite

The three-level dialog act annotation scheme of the DIHANA corpus poses a multi-level classification problem in which the bottom levels allow multiple or no labels for a single segment. We approach automatic dialog act recognition on the three levels using an end-to-end approach, in order to implicitly capture relations between them. Our deep neural network classifier uses a combination of word-and character-based segment representation approaches, together with a summary of the dialog history and information concerning speaker changes. We show that it is important to specialize the generic segment representation in order to capture the most relevant information for each level. On the other hand, the summary of the dialog history should combine information from the three levels to capture dependencies between them. Furthermore, the labels generated for each level help in the prediction of those of the lower levels. Overall, we achieve results which surpass those of our previous approach using the hierarchical combination of three independent per-level classifiers. Furthermore, the results even surpass the results achieved on the simplified version of the problem approached by previous studies, which neglected the multi-label nature of the bottom levels and only considered the label combinations present in the corpus.

show abstract

Unsegmented Dialogue Act Annotation and Decoding with N-Gram Transducers

Cited by 5 publications

References 58 publications

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

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

Joint, Incremental Disfluency Detection and Utterance Segmentation from Speech

End-to-End Multi-Level Dialog Act Recognition

Contact Info

Product

Resources

About