• Home
  • Search
  • Estimating the number of segments for improving dialogue act labelling
  • Cite Icon3
  • https://doi.org/10.1017/s135132491000032xCopy DOI Icon

Estimating the number of segments for improving dialogue act labelling

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Abstract In dialogue systems it is important to label the dialogue turns with dialogue-related meaning. Each turn is usually divided into segments and these segments are labelled with dialogue acts (DAs). A DA is a representation of the functional role of the segment. Each segment is labelled with one DA, representing its role in the ongoing discourse. The sequence of DAs given a dialogue turn is used by the dialogue manager to understand the turn. Probabilistic models that perform DA labelling can be used on segmented or unsegmented turns. The last option is more likely for a practical dialogue system, but it provides poorer results. In that case, a hypothesis for the number of segments can be provided to improve the results. We propose some methods to estimate the probability of the number of segments based on the transcription of the turn. The new labelling model includes the estimation of the probability of the number of segments in the turn. We tested this new approach with two different dialogue corpora:SwitchBoardandDihana. The results show that this inclusion significantly improves the labelling accuracy.

Similar Papers
  • Conference Article
  • Citations3

Towards human-machine dialog in Slovak

  • May 01, 2016
  • Stanislav Ondas +1
  • Book Chapter

Skip Act Vectors: Integrating Dialogue Context into Sentence Embeddings

  • Jan 01, 2021
  • Jeremy Auguste +3
  • Conference Article
  • Citations1

Automatic recognition of dialogue acts in complex typology

  • Jun 01, 2011
  • M Koit
  • PDF
  • Conference Article
  • Citations5

A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System

  • Jan 01, 2018
  • Tianyu Zhao +1
  • Conference Article
  • Citations22

Understanding Student Language: An Unsupervised Dialogue Act Classification Approach

  • Feb 24, 2015
  • Zenodo (CERN European Organization for Nuclear Research)
  • Aysu Ezen-Can +1
  • Conference Article
  • Citations2

Myanmar Dialogue Act Recognition (MDAR)

  • Feb 01, 2020
  • Sann Su Su Yee +2
  • Conference Article
  • Citations21

Bridging the gap between dialogue management and dialogue models

  • Jan 01, 2002
  • Weiqun Xu +3
  • Conference Article
  • Citations2

Development of a machine learnable discourse tagging tool

  • Jan 01, 2001
  • Masahiro Araki +3
  • PDF
  • Conference Article
  • Citations22

Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network

  • Jan 01, 2020
  • Yangming Li +5
  • Conference Article
  • Citations3

Neural Dialogue State Tracking with Temporally Expressive Networks

  • Jan 01, 2020
  • Junfan Chen +3
  • Conference Article

Modelling Negotiation Strategies

  • Jul 01, 2019
  • Mare Koit
  • Conference Article
  • Citations7

Dialogue Management based on Multi-domain Corpus

  • Jan 01, 2015
  • Wendong Ge +1
  • Research Article
  • Citations1

Unsupervised Color Image Segmentation Based on Non Parametric Clustering

  • Jan 01, 2013
  • Journal of Computing and Information Technology
  • Imene Kirati +1
  • Book Chapter
  • Citations1

Incorporating Social Practices in Dialogue Systems

  • Jan 01, 2022
  • Eren Yildiz +2
  • Conference Article
  • Citations11

Weighted finite state transducer based statistical dialog management

  • Dec 01, 2009
  • Chiori Hori +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.