research-article

Conversations Powered by Cross-Lingual Knowledge

Authors:

Maarten de RijkeAuthors Info & Claims

SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

Pages 1442 - 1451

https://doi.org/10.1145/3404835.3462883

Published: 11 July 2021 Publication History

Abstract

Today's open-domain conversational agents increase the informativeness of generated responses by leveraging external knowledge. Most of the existing approaches work only for scenarios with a massive amount of monolingual knowledge sources. For languages with limited availability of knowledge sources, it is not effective to use knowledge in the same language to generate informative responses. To address this problem, we propose the task of cross-lingual knowledge grounded conversation (CKGC), where we leverage large-scale knowledge sources in another language to generate informative responses. Two main challenges come with the task of cross-lingual knowledge grounded conversation: (1) knowledge selection and response generation in a cross-lingual setting; and (2) the lack of a test dataset for evaluation. To tackle the first challenge, we propose the curriculum self-knowledge distillation (CSKD) scheme, which utilizes a large-scale dialogue corpus in an auxiliary language to improve cross-lingual knowledge selection and knowledge expression in the target language via knowledge distillation. To tackle the second challenge, we collect a cross-lingual knowledge grounded conversation test dataset to facilitate relevant research in the future. Extensive experiments on the newly created dataset verify the effectiveness of our proposed curriculum self-knowledge distillation method for cross-lingual knowledge grounded conversation. In addition, we find that our proposed unsupervised method significantly outperforms the state-of-the-art baselines in cross-lingual knowledge selection.

References

[1]

Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, and Quoc V. Le. 2020. Towards a Human-like Open-Domain Chatbot. arXiv preprint arXiv:2001.09977 (2020).

[2]

Mikel Artetxe and Holger Schwenk. 2019. Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings. In ACL .

[3]

Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. Curriculum Learning. In ICML .

[4]

Hongshen Chen, Zhaochun Ren, Jiliang Tang, Yihong Eric Zhao, and Dawei Yin. 2018. Hierarchical Variational Memory Network for Dialogue Generation. In WWW . 1653--1662.

[5]

Yen-Chun Chen, Zhe Gan, Yu Cheng, Jingzhou Liu, and Jing jing Liu. 2020. Distilling Knowledge Learned in BERT for Text Generation. In ACL .

[6]

Zewen Chi, Li Dong, Furu Wei, Wenhui Wang, Xian-Ling Mao, and Heyan Huang. 2020. Cross-lingual Natural Language Generation via Pre-training. In AAAI .

[7]

Kevin Clark and Christopher D. Manning. 2016. Deep Reinforcement Learning for Mention-Ranking Coreference Models. In EMNLP .

[8]

Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised Cross-lingual Representation Learning at Scale. In ACL .

[9]

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT .

[10]

Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2019. Wizard of Wikipedia: Knowledge-Powered Conversational Agents. ICLR .

[11]

Xiangyu Duan, Mingming Yin, Min Zhang, Boxing Chen, and Weihua Luo. 2019. Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention. In ACL .

[12]

Fangxiaoyu Feng, Yin-Fei Yang, Daniel Matthew Cer, Naveen Arivazhagan, and Wei Wang. 2020. Language-agnostic BERT Sentence Embedding. arXiv preprint arXiv:2007.01852 (2020).

[13]

Joseph L. Fleiss. 1971. Measuring Nominal Scale Agreement among Many Raters. Psychological Bulletin, Vol. 76 (1971), 378--382.

[14]

Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, and Tat-Seng Chua. 2021. Advances and Challenges in Conversational Recommender Systems: A Survey. arXiv preprint arXiv:2101.09459 (January 2021).

[15]

Edouard Grave, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, and Tomas Mikolov. 2018. Learning Word Vectors for 157 Languages. arXiv preprint arXiv:1802.06893 (2018).

[16]

Sangchul Hahn and Heeyoul Choi. 2019. Self-Knowledge Distillation in Natural Language Processing. In RANLP .

[17]

Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015).

[18]

Zhuolin Jiang, Amro El-Jaroudi, William Hartmann, Damianos Karakos, and Lingjun Zhao. 2020. Cross-lingual Information Retrieval with BERT. arXiv preprint arXiv:2004.13005 (2020).

[19]

Xisen Jin, Wenqiang Lei, Zhaochun Ren, Hongshen Chen, Shangsong Liang, Yihong Zhao, and Dawei Yin. 2018. Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation. In CIKM . 1403--1412.

[20]

Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2017. Billion-scale Similarity Search with GPUs. arXiv preprint arXiv:1702.08734 (2017).

[21]

Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2017. Bag of Tricks for Efficient Text Classification. In EACL .

[22]

Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, and Tat-Seng Chua. 2020. Estimation-action-reflection: Towards Deep Interaction between Conversational and Recommender Systems. In WSDM. 304--312.

[23]

Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, and Dawei Yin. 2018. Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-sequence Architectures. In ACL. 1437--1447.

[24]

Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2015. A Diversity-Promoting Objective Function for Neural Conversation Models. NAACL .

[25]

Lin-Xiao Li, Can Xu, W. Wu, Yufan Zhao, Xueliang Zhao, and Chongyang Tao. 2020. Zero-Resource Knowledge-Grounded Dialogue Generation. NeurIPS .

[26]

Rongzhong Lian, Min Xie, Fan Wang, Jinhua Peng, and Hua Wu. 2019. Learning to Select Knowledge for Response Generation in Dialog Systems. IJCAI .

[27]

Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In ACL .

[28]

Robert Litschko, Goran Glavas, Simone Paolo Ponzetto, and Ivan Vulic. 2018. Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only. SIGIR (2018).

[29]

Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, and Dawei Yin. 2018. Knowledge Diffusion for Neural Dialogue Generation. In ACL .

[30]

Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020. Multilingual Denoising Pre-training for Neural Machine Translation. TACL (2020).

[31]

Longxuan Ma, Weinan Zhang, Runxin Sun, and Ting Liu. 2020 b. A Compare Aggregate Transformer for Understanding Document-grounded Dialogue. In Findings of EMNLP .

[32]

Longxuan Ma, Wei-Nan Zhang, Mingda Li, and Ting Liu. 2020 a. A Survey of Document Grounded Dialogue Systems (DGDS). arXiv preprint arXiv:2004.13818 (2020).

[33]

Chuan Meng, Pengjie Ren, Zhumin Chen, Christof Monz, Jun Ma, and Maarten de Rijke. 2020 a. RefNet: A Reference-aware Network for Background Based Conversation. In AAAI .

[34]

Chuan Meng, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Tengxiao Xi, and Maarten de Rijke. 2021. Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations. In SIGIR . ACM.

[35]

Chuan Meng, Pengjie Ren, Zhumin Chen, Weiwei Sun, Zhaochun Ren, Zhaopeng Tu, and Maarten de Rijke. 2020 b. DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation. In SIGIR . ACM.

[36]

Jian-Yun Nie. 2010. Cross-Language Information Retrieval .Morgan & Claypool.

[37]

Vassilina Nikoulina, Bogomil Kovachev, Nikolaos Lagos, and Christof Monz. 2012. Adaptation of Statistical Machine Translation Model for Cross-Lingual Information Retrieval in a Service Context. In EACL .

[38]

Douglas W. Oard. 1998. A Comparative Study of Query and Document Translation for Cross-Language Information Retrieval. In AMTA .

[39]

Prasanna Parthasarathi and Joelle Pineau. 2018. Extending Neural Generative Conversational Model using External Knowledge Sources. In EMNLP .

[40]

Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Póczos, and Tom Michael Mitchell. 2019. Competence-based Curriculum Learning for Neural Machine Translation. In NAACL .

[41]

Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners.

[42]

Pengjie Ren, Zhumin Chen, Zhaochun Ren, Evangelos Kanoulas, Christof Monz, and Maarten de Rijke. 2020. Conversations with Search Engines. arXiv preprint arXiv:2004.14162 (2020).

[43]

Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. 1994. Okapi at TREC-3. In TREC .

[44]

Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. 2016. Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models. In AAAI .

[45]

Siamak Shakeri, Abhinav Sethy, and Cheng Cheng. 2019. Knowledge Distillation in Document Retrieval. AMLC (2019).

[46]

Haipeng Sun, Rui Wang, Kehai Chen, M. Utiyama, Eiichiro Sumita, and Tiejun Zhao. 2020. Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation. arXiv preprint arXiv:2004.10171 (2020).

[47]

Richard S. Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In NIPS .

[48]

Jö rg Tiedemann and Santhosh Thottingal. 2020. OPUS-MT -- Building open translation services for the World. In EAMT .

[49]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. NIPS .

[50]

Oriol Vinyals and Quoc V. Le. 2015. A Neural Conversational Model. arXiv preprint arXiv:1506.05869 (2015).

[51]

Ivan Vulic and Marie-Francine Moens. 2015. Monolingual and Cross-Lingual Information Retrieval Models Based on (Bilingual) Word Embeddings. SIGIR (2015).

[52]

Jun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, and Ting Liu. 2020. Conversational Graph Grounded Policy Learning for Open-domain Conversation Generation. In ACL . 1835--1845.

[53]

Ruochen Xu and Yiming Yang. 2017. Cross-lingual Distillation for Text Classification. ACL (2017).

[54]

Ze Yang, Linjun Shou, Ming Gong, Wutao Lin, and Daxin Jiang. 2020. Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System. WSDM (2020).

[55]

Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2020. DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation. In ACL .

[56]

Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao, Dongyan Zhao, and Rui Yan. 2020. Knowledge-Grounded Dialogue Generation with Pre-trained Language Models. In EMNLP .

[57]

Dong Zhou, Mark Truran, Tim Brailsford, Vincent Wade, and Helen Ashman. 2012. Translation Techniques in Cross-language Information Retrieval. Comput. Surveys, Vol. 45, 1 (2012), Article 1.

Digital Library

[58]

Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. 2018. Commonsense Knowledge Aware Conversation Generation with Graph Attention. In IJCAI .

Cited By

Di DSong XZhang WZhang YWang F(2023)Building Dialogue Understanding Models for Low-resource Language Indonesian from ScratchACM Transactions on Asian and Low-Resource Language Information Processing10.1145/357580322:4(1-20)Online publication date: 6-Apr-2023
https://dl.acm.org/doi/10.1145/3575803
Lei WGao Cde Rijke M(2021)RecSys 2021 Tutorial on Conversational Recommendation: Formulation, Methods, and EvaluationProceedings of the 15th ACM Conference on Recommender Systems10.1145/3460231.3473325(842-844)Online publication date: 13-Sep-2021
https://dl.acm.org/doi/10.1145/3460231.3473325
Sun WZhang SBalog KRen ZRen PChen Zde Rijke MDiaz FShah CSuel TCastells PJones RSakai T(2021)Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue SystemsProceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3404835.3463241(2499-2506)Online publication date: 11-Jul-2021
https://dl.acm.org/doi/10.1145/3404835.3463241
Show More Cited By

Index Terms

Conversations Powered by Cross-Lingual Knowledge
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
      1. Discourse, dialogue and pragmatics
      2. Natural language generation

Recommendations

Initiative-Aware Self-Supervised Learning for Knowledge-Grounded Conversations
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

In the knowledge-grounded conversation (KGC) task systems aim to produce more informative responses by leveraging external knowledge. KGC includes a vital part, knowledge selection, where conversational agents select the appropriate knowledge to be ...
DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

Today's conversational agents often generate responses that not sufficiently informative. One way of making them more informative is through the use of of external knowledge sources with so-called Knowledge-Grounded Conversations (KGCs). In this paper, ...
Semantic morphological variant selection and translation disambiguation for cross-lingual information retrieval
Abstract
Cross-Lingual Information Retrieval (CLIR) enables a user to query in a language which is different from the target documents language. CLIR incorporates a translation technique based on either a manual dictionary or a probabilistic dictionary ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

July 2021

2998 pages

ISBN:9781450380379

DOI:10.1145/3404835

General Chairs:
Fernando Diaz
(Google)
,
Chirag Shah
University of Washington
,
Torsten Suel
New York University
,
Program Chairs:
Pablo Castells
Universidad Autónoma de Madrid, Amazon
,
Rosie Jones
Spotify
,
Tetsuya Sakai
Waseda University

Copyright © 2021 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 the author(s) 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: 11 July 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Natural Science Foundation of China
Tencent WeChat Rhino-Bird Focused Research Program
National Key R&D Program of China
Key Scientific and Technological Innovation Program of Shandong Province

Conference

SIGIR '21

Sponsor:

SIGIR

SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

July 11 - 15, 2021

Virtual Event, Canada

Acceptance Rates

Overall Acceptance Rate 792 of 3,983 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
441
Total Downloads

Downloads (Last 12 months)35
Downloads (Last 6 weeks)3

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Di DSong XZhang WZhang YWang F(2023)Building Dialogue Understanding Models for Low-resource Language Indonesian from ScratchACM Transactions on Asian and Low-Resource Language Information Processing10.1145/357580322:4(1-20)Online publication date: 6-Apr-2023
https://dl.acm.org/doi/10.1145/3575803
Lei WGao Cde Rijke M(2021)RecSys 2021 Tutorial on Conversational Recommendation: Formulation, Methods, and EvaluationProceedings of the 15th ACM Conference on Recommender Systems10.1145/3460231.3473325(842-844)Online publication date: 13-Sep-2021
https://dl.acm.org/doi/10.1145/3460231.3473325
Sun WZhang SBalog KRen ZRen PChen Zde Rijke MDiaz FShah CSuel TCastells PJones RSakai T(2021)Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue SystemsProceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3404835.3463241(2499-2506)Online publication date: 11-Jul-2021
https://dl.acm.org/doi/10.1145/3404835.3463241
Meng CRen PChen ZRen ZXi TRijke MDiaz FShah CSuel TCastells PJones RSakai T(2021)Initiative-Aware Self-Supervised Learning for Knowledge-Grounded ConversationsProceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3404835.3462824(522-532)Online publication date: 11-Jul-2021
https://dl.acm.org/doi/10.1145/3404835.3462824

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