• Home
  • Search
  • Skip Act Vectors: Integrating Dialogue Context into Sentence Embeddings
  • https://doi.org/10.1007/978-981-15-9323-9_1Copy DOI Icon

Skip Act Vectors: Integrating Dialogue Context into Sentence Embeddings

  • Jan 1, 2021
  • Jeremy Auguste +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

This paper compares several approaches for computing dialogue turn embeddings and evaluate their representation capacities in two dialogue act related tasks within a hierarchical Recurrent Neural Network architecture. These turn embeddings can be produced explicitely or implicitely by extracting the hidden layer of a model trained for a given task. We introduce skip-act, a new dialogue turn embeddings approach, which are extracted as the common representation layer from a multi-task model that predicts both the previous and the next dialogue act. The models used to learn turn embeddings are trained on a large dialogue corpus with light supervision, while the models used to predict dialog acts using turn embeddings are trained on a sub-corpus with gold dialogue act annotations. We compare their performances for predicting the current dialogue act as well as their ability to predict the next dialogue act, which is a more challenging task that can have several applicative impacts. With a better context representation, the skip-act turn embeddings are shown to outperform previous approaches both in terms of overall F-measure and in terms of macro-F1, showing regular improvements on the various dialogue acts.

Similar Papers
  • 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
  • Research Article
  • Citations3

Estimating the number of segments for improving dialogue act labelling

  • Feb 14, 2011
  • Natural Language Engineering
  • Vicent Tamarit +2
  • Conference Article
  • Citations4

Hierarchical artificial neural network architecture

  • May 04, 1998
  • R.K Speer +1
  • PDF
  • Conference Article
  • Citations27

Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension

  • Jan 01, 2019
  • Zhengyuan Liu +1
  • Research Article
  • Citations60

Super-resolution visualization of subwavelength defects via deep learning-enhanced ultrasonic beamforming: A proof-of-principle study

  • Aug 15, 2020
  • NDT & E International
  • Homin Song +1
  • Conference Article
  • Citations19

Towards real-time hyperspectral image processing, a GP-GPU implementation of target identification

  • Sep 01, 2011
  • D B Heras +4
  • Research Article
  • Citations36

MFC-CNN: An automatic grading scheme for light stress levels of lettuce (Lactuca sativa L.) leaves

  • Oct 30, 2020
  • Computers and Electronics in Agriculture
  • Xia Hao +6
  • Research Article
  • Citations17

Pkg2Vec: Hierarchical package embedding for code authorship attribution

  • Oct 23, 2020
  • Future Generation Computer Systems
  • Roni Mateless +2
  • PDF
  • Research Article
  • Citations11

A Hybrid 3D–2D Feature Hierarchy CNN with Focal Loss for Hyperspectral Image Classification

  • Sep 09, 2023
  • Remote Sensing
  • Xiaoyan Wen +4
  • Book Chapter
  • Citations4

A Hierarchical Neural Network Model for Pattern Recognition

  • Jan 01, 1997
  • Steffen Simon +2
  • PDF
  • Research Article
  • Citations26

A Novel Approach for Modeling Neural Responses to Joint Perturbations Using the NARMAX Method and a Hierarchical Neural Network

  • Dec 06, 2018
  • Frontiers in Computational Neuroscience
  • Runfeng Tian +3
  • Conference Article
  • Citations1

Hierarchical underwater acoustic sensor networks with (virtual) transmit/receive arrays

  • Dec 01, 2011
  • Andrej Stefanov +1
  • Research Article
  • Citations1

SVMobileNetV2: A Hybrid and Hierarchical CNN-SVM Network Architecture Utilising UAV-Based Multispectral Images and IoT Nodes for the Precise Classification of Crop Diseases

  • Oct 10, 2025
  • AgriEngineering
  • Rafael Linero-Ramos +2
  • Research Article
  • Citations53

HGNN: Hierarchical graph neural network for predicting the classification of price-limit-hitting stocks

  • Jun 11, 2022
  • Information Sciences
  • Cong Xu +8
  • Research Article
  • Citations5

Navigation behavior based on self-organized spatial representation in hierarchical recurrent neural network

  • Jan 16, 2019
  • Advanced Robotics
  • Wataru Noguchi +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.