research-article

Length Adaptive Regularization for Retrieval-based Chatbot Models

Authors:

Hui FangAuthors Info & Claims

ICTIR '20: Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval

Pages 113 - 120

https://doi.org/10.1145/3409256.3409823

Published: 14 September 2020 Publication History

Abstract

Chatbots aim to mimic real conversations between humans. They have started playing an increasingly important role in our daily life. Given past conversations, a retrieval-based chatbot model selects the most appropriate response from a pool of candidates. Intuitively, based on the nature of the conversations, some responses are expected to be long and informative while others need to be more concise. Unfortunately, none of the existing retrieval-based chatbot models have considered the effect of response length. Empirical observations suggested the existing models over-favor longer candidate responses, leading to sub-optimal performance.

To overcome this limitation, we propose a length adaptive regularization method for retrieval-based chatbot models. Specifically, we first predict the desired response length based on the conversation context and then apply a regularization method based on the predicted length to adjust matching scores for candidate responses. The proposed length adaptive regularization method is general enough to be applied to all existing retrieval-based chatbot models. Experiments on two public data sets show the proposed method is effective to significantly improve retrieval performance.

References

[1]

Mehdi Assefi, Guangchi Liu, Mike P Wittie, and Clemente Izurieta. 2015. An Experimental Evaluation of Apple Siri and Google Speech Recognition. ISCA SEDE (2015), 1--6.

[2]

Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv e-prints, Article arXiv:1412.3555 (2014).

[3]

J. H S Griffith. 1966. ELIZA - A Computer Program For the study of Natural Language Communication Betweeen Man and Machine. Communication of the ACM (1966), 36--45.

[4]

Matthew Henderson, Rami Al-Rfou, Brian Strope, Yun-hsuan Sung, Laszlo Lukacs, Ruiqi Guo, Sanjiv Kumar, Balint Miklos, and Ray Kurzweil. 2017. Efficient Natural Language Response Suggestion for Smart Reply. arXiv e-prints (2017). arxiv: cs.CL/1705.00652

[5]

Matthew Henderson, Ivan Vulić, Daniela Gerz, I nigo Casanueva, Paweł Budzianowski, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrkvs ić, and Pei-Hao Su. 2019. Training Neural Response Selection for Task-Oriented Dialogue Systems. arXiv e-prints (2019). arxiv: cs.CL/1906.01543

[6]

Jiwei Li, Michel Galley, Chris Brockett, Georgios P. Spithourakis, Jianfeng Gao, and Bill Dolan. 2016. A Persona-Based Neural Conversation Model. ACL (2016), 994--1003.

[7]

Bingquan Liu, Zhen Xu, Chengjie Sun, Baoxun Wang, Xiaolong Wang, Derek F. Wong, and Min Zhang. 2018. Content-Oriented User Modeling for Personalized Response Ranking in Chatbots. TASLP (2018), 122--133.

[8]

Ryan Lowe, Nissan Pow, Iulian Vlad, Laurent Charlin, Chia-Wei Liu, and Joelle Pineau. 2017. Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus. Dialogue & Discourse, Vol. 8, 1 (2017), 31--65.

[9]

Yi Luan, Yangfeng Ji, and Mari Ostendorf. 2016. LSTM based Conversation Models. arXiv e-prints (Mar 2016). arxiv: cs.CL/1603.09457

[10]

Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. ICLR (2013), 1--12.

[11]

Minghui Qiu, Feng-Lin Li, Siyu Wang, Xing Gao, Yan Chen, Weipeng Zhao, Haiqing Chen, Jun Huang, and Wei Chu. 2017. AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine. ACL (2017), 498--503.

[12]

Lebuhraya Tun Razak. 2010. One-Match and All-Match Categories for Keywords Matching in Chatbot. American Journal of Applied Sciences (2010), 1406--1411.

[13]

Taihua Shao, Fei Cai, Honghui Chen, and Maarten Rijke. 2019. Length-adaptive Neural Network for Answer Selection. SIGIR (2019), 869--872.

[14]

Heung-Yeung Shum, Xiaodong He, and Di Li. 2018. From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots. Frontiers of Information Technology and Electronic Engineering (2018), 10--26.

[15]

Amit Singhal, Chris Buckley, and Mandar Mitra. 1996. Pivoted Document Length Normalization. SIGIR (1996), 21--29.

[16]

Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. arXiv e-prints (2015). arxiv: cs.CL/1506.06714

[17]

Chongyang Tao, Wei Wu, Can Xu, Wenpeng Hu, Dongyan Zhao, and Rui Yan. 2019. Multi-reprentation Fusion Network for Multi-Turn Response Selection in Retrieval-Based Chatbots. WSDM (2019), 267--275.

[18]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR (2017), 5998--6008.

[19]

Richard S Wallace. 2002. El programa Artificial Linguistic Internet Computer Entity (A.L.I.C.E.). Computation Systems (2002), 14--21.

[20]

Disen Wang and Hui Fang. 2020. An Adaptive Response Matching Network for Ranking Multi-turn Chatbot Responses. NLDB (2020), 239--251.

[21]

Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017. A Network-based End-to-End Trainable Task-oriented Dialogue System. ACL (2017), 438--449.

[22]

Yu Wu, Wei Wu, Chen Xing, Can Xu, Zhoujun Li, and Ming Zhou. 2017. A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots. ACL (2017), 496--505.

[23]

Liu Yang, Jun Huang, Haiqing Chen, and W Bruce Croft. 2018. Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems. SIGIR (2018), 245--254.

[24]

Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, and Hua Wu. 2018. Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network. ACL (2018), 1118--1127.

Cited By

Lin XZhang ZYue PLi HZhang JFan BSu HGong X(2024)SyncIntellects: Orchestrating LLM Inference with Progressive Prediction and QoS-Friendly Control2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)10.1109/IWQoS61813.2024.10682949(1-10)Online publication date: 19-Jun-2024
https://doi.org/10.1109/IWQoS61813.2024.10682949
Jin YChen LCai WPu P(2021)Key Qualities of Conversational Recommender Systems: From Users’ PerspectiveProceedings of the 9th International Conference on Human-Agent Interaction10.1145/3472307.3484164(93-102)Online publication date: 9-Nov-2021
https://dl.acm.org/doi/10.1145/3472307.3484164
Xain AGoyal ASingh BSharma S(2020)Multilinguistic approach towards Information Retrieval System for Big Data2020 3rd International Conference on Intelligent Sustainable Systems (ICISS)10.1109/ICISS49785.2020.9315969(159-164)Online publication date: 3-Dec-2020
https://doi.org/10.1109/ICISS49785.2020.9315969

Index Terms

Length Adaptive Regularization for Retrieval-based Chatbot Models
1. Information systems
  1. Information retrieval
    1. Retrieval models and ranking
      1. Learning to rank
      2. Top-k retrieval in databases

Recommendations

Memory-Based Matching Models for Multi-turn Response Selection in Retrieval-Based Chatbots
Natural Language Processing and Chinese Computing
Abstract
This paper describes the system we submitted to Task 5 in NLPCC 2018, i.e., Multi-Turn Dialogue System in Open-Domain. This work focuses on the second subtask: Retrieval Dialogue System. Given conversation sessions and 10 candidates for each ...
A comprehensive solution to retrieval-based chatbot construction
Abstract
In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents. In contrast to most existing research ...
Highlights
- Comprehensive solution to build retrieval-based chatbots for a large scale application.
Memory-Based Model with Multiple Attentions for Multi-turn Response Selection
Neural Information Processing
Abstract
In this paper, we study the task of multi-turn response selection in retrieval-based dialogue systems. Previous approaches focus on matching response with utterances in the context to distill important matching information, and modeling sequential ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICTIR '20: Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval

September 2020

207 pages

ISBN:9781450380676

DOI:10.1145/3409256

General Chairs:
Krisztian Balog
University of Stavanger, Norway
,
Vinay Setty
University of Stavanger, Norway
,
Program Chairs:
Christina Lioma
University of Copenhagen, Denmark
,
Yiqun Liu
Tsinghua University, China
,
Min Zhang
Tsinghua University, China
,
Klaus Berberich
HTW Saar & MPI for Informatics, Germany

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGIR: ACM Special Interest Group on Information Retrieval

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 14 September 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

ICTIR '20

Sponsor:

SIGIR

ICTIR '20: The 2020 ACM SIGIR International Conference on the Theory of Information Retrieval

September 14 - 17, 2020

Virtual Event, Norway

Acceptance Rates

Overall Acceptance Rate 235 of 527 submissions, 45%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
201
Total Downloads

Downloads (Last 12 months)18
Downloads (Last 6 weeks)3

Reflects downloads up to 09 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Lin XZhang ZYue PLi HZhang JFan BSu HGong X(2024)SyncIntellects: Orchestrating LLM Inference with Progressive Prediction and QoS-Friendly Control2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)10.1109/IWQoS61813.2024.10682949(1-10)Online publication date: 19-Jun-2024
https://doi.org/10.1109/IWQoS61813.2024.10682949
Jin YChen LCai WPu P(2021)Key Qualities of Conversational Recommender Systems: From Users’ PerspectiveProceedings of the 9th International Conference on Human-Agent Interaction10.1145/3472307.3484164(93-102)Online publication date: 9-Nov-2021
https://dl.acm.org/doi/10.1145/3472307.3484164
Xain AGoyal ASingh BSharma S(2020)Multilinguistic approach towards Information Retrieval System for Big Data2020 3rd International Conference on Intelligent Sustainable Systems (ICISS)10.1109/ICISS49785.2020.9315969(159-164)Online publication date: 3-Dec-2020
https://doi.org/10.1109/ICISS49785.2020.9315969
Jin YChen LCai WZhao X(undefined)CRS-Que: A User-Centric Evaluation Framework for Conversational Recommender SystemsACM Transactions on Recommender Systems10.1145/3631534
https://dl.acm.org/doi/10.1145/3631534

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten