Speaker-change Aware CRF for Dialogue Act Classification

Abstract

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.

arXiv commenttypo fix: argmin -> argmax

References in corpus (10)

• Efficient Estimation of Word Representations in Vector Space
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
• TENER: Adapting Transformer Encoder for Named Entity Recognition
• Recurrent Convolutional Neural Networks for Discourse Compositionality
• Hierarchically-Refined Label Attention Network for Sequence Labeling
• Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection
• Transfer Learning for Sequence Labeling Using Source Model and Target Data
• Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding
• LinTO : Assistant vocal open-source respectueux des données personnelles pour les réunions d'entreprise