Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer.CRF models the conditional probability of the target DA label sequence given the input utterance sequence.However, the task involves another important input sequence, that of speakers, which is ignored by previous work.To address this limitation, this paper proposes a simple modification of the CRF layer that takes speaker-change into account.Experiments on the SwDA corpus show that our modified CRF layer outperforms the original one, with very wide margins for some DA labels.Further, visualizations demonstrate that our CRF layer can learn meaningful, sophisticated transition patterns between DA label pairs conditioned on speaker-change in an end-to-end way.Code is publicly available 1 .

This paper investigates the advantages and limits of data programming for the task of learning discourse structure.The data programming paradigm implemented in the Snorkel framework allows a user to label training data using expert-composed heuristics, which are then transformed via the "generative step" into probability distributions of the class labels given the training candidates.These results are later generalized using a discriminative model.Snorkel's attractive promise to create a large amount of annotated data from a smaller set of training data by unifying the output of a set of heuristics has yet to be used for computationally difficult tasks, such as that of discourse attachment, in which one must decide where a given discourse unit attaches to other units in a text in order to form a coherent discourse structure.Although approaching this problem using Snorkel requires significant modifications to the structure of the heuristics, we show that weak supervision methods can be more than competitive with classical supervised learning approaches to the attachment problem.

Sonia Badene, Kate Thompson, Jean-Pierre Lorré, Nicholas Asher. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

International audience

Guokan Shang, Wensi Ding, Zekun Zhang, Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis, Jean-Pierre Lorré. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

Deep learning based systems have greatly improved the performance in speech recognition tasks, and various deep architectures and learning methods have been developed in the last few years. Along with that, Data Augmentation (DA), which is a common strategy adopted to increase the quantity of training data, has been shown to be effective for neural network training to make invariant predictions. On the other hand, Ensemble Method (EM) approaches have received considerable attention in the machine learning community to increase the effectiveness of classifiers. Therefore, we propose in this work a new Deep Neural Network (DNN) speech recognition architecture which takes advantage from both DA and EM approaches in order to improve the prediction accuracy of the system. In this paper, we first explore an existing approach based on vocal tract length perturbation and we propose a different DA technique based on feature perturbation to create a modified training data sets. Finally, EM techniques are used to integrate the posterior probabilities produced by different DNN acoustic models trained on different data sets. Experimental results demonstrate an increase in the recognition performance of the proposed system.

In model-driven learning, simulation of Business Process is a key step for improving the learners's skills and enhancing teaching performance. In this paper, we provide the architectural design and the main functionalities of a model-based learning simulation framework. The main objectives of the proposed framework are: i) enable user-friendly learning simulation with a strong support for collaboration and social interactions; ii) provide a process-driven learning environment that allows emulation of the learner behavior when no learners are available to be involved on the simulation; iii) include event-based monitoring aiming at providing feedbacks for the learner assessment.