DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 58 references that are in the map. First posted on arXiv 25 Oct 2022.
Builds on
32 of 58 references.
References · 32
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2014Going Deeper with Convolutionscited by 4,231
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
- 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
20 more
- 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
- 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
- 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
- 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
- 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 131
- 2020Lite Transformer with Long-Short Range Attentioncited by 127
- 2020MuTual: A Dataset for Multi-Turn Dialogue Reasoningcited by 114
- 2016Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbotscited by 103
- 2020Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbotscited by 73
- 2017On Sampling Strategies for Neural Network-based Collaborative Filteringcited by 71
- 2018Modeling Multi-turn Conversation with Deep Utterance Aggregationcited by 65
- 2016Machine Comprehension Using Match-LSTM and Answer Pointercited by 47
- 2019Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Studycited by 47
- 2021Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterancescited by 40
- 2015A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representationscited by 32
- 2015LSTM-based Deep Learning Models for Non-factoid Answer Selectioncited by 17
- 2019Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbotscited by 14
- 2019Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbotscited by 13
- 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
- 2020A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-trainingcited by 9
Built on by
Citing papers per year: 2023: 1.
1 paper.