Guiding attention in Sequence-to-sequence models for Dialogue Act prediction

02/20/2020
by   Pierre Colombo, et al.
0

The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents. Accurately predicting DAs requires a precise modeling of both the conversation and the global tag dependencies. We leverage seq2seq approaches widely adopted in Neural Machine Translation (NMT) to improve the modelling of tag sequentiality. Seq2seq models are known to learn complex global dependencies while currently proposed approaches using linear conditional random fields (CRF) only model local tag dependencies. In this work, we introduce a seq2seq model tailored for DA classification using: a hierarchical encoder, a novel guided attention mechanism and beam search applied to both training and inference. Compared to the state of the art our model does not require handcrafted features and is trained end-to-end. Furthermore, the proposed approach achieves an unmatched accuracy score of 85 MRDA.

READ FULL TEXT
research
02/21/2020

Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue

The task of predicting dialog acts (DA) based on conversational dialog i...
research
10/28/2017

A Dual Encoder Sequence to Sequence Model for Open-Domain Dialogue Modeling

Ever since the successful application of sequence to sequence learning f...
research
02/28/2019

Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

This paper presents our latest investigations on dialog act (DA) classif...
research
04/06/2020

Speaker-change Aware CRF for Dialogue Act Classification

Recent work in Dialogue Act (DA) classification approaches the task as a...
research
10/04/2019

Multi-level Gated Recurrent Neural Network for Dialog Act Classification

In this paper we focus on the problem of dialog act (DA) labelling. This...
research
08/16/2017

Dialogue Act Segmentation for Vietnamese Human-Human Conversational Texts

Dialog act identification plays an important role in understanding conve...
research
11/15/2017

Dialogue Act Recognition via CRF-Attentive Structured Network

Dialogue Act Recognition (DAR) is a challenging problem in dialogue inte...

Please sign up or login with your details

Forgot password? Click here to reset