DialogConv: A lightweight fully convolutional network for multi-view response selection

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel li...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU, Yongkang, FENG, Shi, GAO, Wei, WANG, Daling, ZHANG, Yifei
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7678
https://ink.library.smu.edu.sg/context/sis_research/article/8681/viewcontent/DialogConv.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8681
record_format dspace
spelling sg-smu-ink.sis_research-86812023-01-10T03:36:59Z DialogConv: A lightweight fully convolutional network for multi-view response selection LIU, Yongkang FENG, Shi GAO, Wei WANG, Daling ZHANG, Yifei Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection. DialogConv is exclusively built on top of convolution to extract matching features of context and response. Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views. On the four benchmark datasets, compared with state-of-the-art baselines, DialogConv is on average about 8.5x smaller in size, and 79.39x and 10.64x faster on CPU and GPU devices, respectively. At the same time, DialogConv achieves the competitive effectiveness of response selection. 2022-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7678 info:doi/10.48550/arXiv.2210.13845 https://ink.library.smu.edu.sg/context/sis_research/article/8681/viewcontent/DialogConv.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
LIU, Yongkang
FENG, Shi
GAO, Wei
WANG, Daling
ZHANG, Yifei
DialogConv: A lightweight fully convolutional network for multi-view response selection
description Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or huge number of parameters. In this paper, we propose a novel lightweight fully convolutional architecture, called DialogConv, for response selection. DialogConv is exclusively built on top of convolution to extract matching features of context and response. Dialogues are modeled in 3D views, where DialogConv performs convolution operations on embedding view, word view and utterance view to capture richer semantic information from multiple contextual views. On the four benchmark datasets, compared with state-of-the-art baselines, DialogConv is on average about 8.5x smaller in size, and 79.39x and 10.64x faster on CPU and GPU devices, respectively. At the same time, DialogConv achieves the competitive effectiveness of response selection.
format text
author LIU, Yongkang
FENG, Shi
GAO, Wei
WANG, Daling
ZHANG, Yifei
author_facet LIU, Yongkang
FENG, Shi
GAO, Wei
WANG, Daling
ZHANG, Yifei
author_sort LIU, Yongkang
title DialogConv: A lightweight fully convolutional network for multi-view response selection
title_short DialogConv: A lightweight fully convolutional network for multi-view response selection
title_full DialogConv: A lightweight fully convolutional network for multi-view response selection
title_fullStr DialogConv: A lightweight fully convolutional network for multi-view response selection
title_full_unstemmed DialogConv: A lightweight fully convolutional network for multi-view response selection
title_sort dialogconv: a lightweight fully convolutional network for multi-view response selection
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/7678
https://ink.library.smu.edu.sg/context/sis_research/article/8681/viewcontent/DialogConv.pdf
_version_ 1770576412614328320