research-article

Chinese Live-streaming Barrage Chatbot Combined with User Vectors

Authors:

Yuan LiuAuthors Info & Claims

CCEAI '21: Proceedings of the 5th International Conference on Control Engineering and Artificial Intelligence

Pages 9 - 15

https://doi.org/10.1145/3448218.3448228

Published: 15 February 2021 Publication History

Abstract

The barrage is a communication method in the webcast environment. It has the characteristics of freedom and openness, fun and vividness. However, the live barrage often mixes content that deviates from mainstream values. In order to better manage the content of the barrage and guide the barrage to a good direction, this research proposed a barrage generation robot algorithm that are allowed to automatically generate high quality responses, called Chinese live barrage chatbot (CLBC). First, according to the characteristics of barrage data, the paper proposed a Barrage Value Function to build a high-quality barrage datasets. Next, CLBC constructed a CLBC model combined with user vectors and transformer. Finally, CLBC designed a barrage text classifier to detect the quality of the barrage generated by itself. The training and testing of a 78,370 pairs of the Barrage Q&A dataset show that CLBC is able to generate more interesting responses and it perform well as the leading seq2seq and transformer question-and-answer system on many indicators such as perplexity, BLEU and barrage text classifier F1 score.

References

[1]

Cho K, Merrenboer B, Bahdanau D, et al. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. ACL SIGDAT, 2014:1724--1734.

[2]

Gehring J, Auli M, Grangier D, et al. Convolutional Sequence to Sequence Learnings. In Advances in neural information processing systems, 3104--3112. 2014.

[3]

Kyunghyun Cho, Bart van Merrenboer, Caglar Gulcehre Dzmitry Bahdanau, et al. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine. In Empirical Methods on Natural Language Processing, 1724--1734.2014.

[4]

Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate. Retrieved December 10, 2018 from https://arxiv.org/pdf/1409.0473v4.pdf

[5]

Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need. Thirty-first Conference on Neural Information Processing Systems. NIPS, 2017: 5998--6008.

[6]

Sordoni A, Galley M, Auli M, et al. A neural network approach to context-sensitive generation of conversation responses. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT 2015). NAACL, 2015:196--205.

[7]

Taihua Shao, Yupu Guo, Honghui Chen, Zepeng Hao. Transformer-Based Neural Network for Answer Selection in Question Answering. IEEE Access, vol. 7, pp. 26146--26156, 2019.

[8]

Shanshan Liu, Sheng Zhang, Xin Zhang. R-Trans: RNN Transformer Network for Chinese Machine Reading Comprehension. IEEE Access, vol. 7, pp. 27736--27745, 2019.

[9]

Youngmin Park, and Sangwoo Kang. Natural Language Generation Using Dependency Tree Decoding for Spoken Dialog Systems. IEEE Access, vol. 7, pp. 7250--7258, 2018.

[10]

Dai Z, Yang Z, Yang Y. Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. ACL, 2019:2978--2988.

[11]

Dehghani M, Gouws S, Vinyals O. Universal Transformers. Retrieved March 05, 2019 from https://arxiv.org/pdf/1807.03819.pdf

[12]

Ma1 S, Lei C, Dai1 D, et al. LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts. Thirty-Third AAAI Conference on Artificial Intelligence. AAAI, 2019:1636--1645.

[13]

Li J, Galley M, Brockett C, et al. A Persona-Based Neural Conversation Model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL, 2016:994--1003.

[14]

Wang X, Liu Y. Research on distributed danmark crawling for China live-broadcasting service.Computer Applications and Software, 134--140. 2018.

[15]

Wang X, Liu Y. Chinese live-streaming danmaku new word detection based on boundary boosting. Transducer and Microsystem Technologies, 142--146+150. 2018.

[16]

Li J, Monroe W, Ritter A, et al. Deep Reinforcement Learning for Dialogue Generation. Retrieved September 29, 2016 from https://arxiv.org/pdf/1606.01541.pdf

[17]

Cao D. 2017. Research on reinforcement learning for open domain chatbot dialogue generation. M.D. Thesis, Harbin Institute of technology.

[18]

Arora S, Liang Y, Ma T. A Simple but Tough-to-Beat Baseline for Sentence Embeddings, International Conference on Learning Representations. 2016. https://openreview.net/pdf?id=SyK00v5xx, 2016-11-4.

[19]

Kannan A, Vinyals O. Adversarial Evaluation of Dialogue Models. Retrieved January 27, 2017 from https://arxiv.org/pdf/1701.08198.pdf

[20]

Kingma D, Ba J. Adam: A method for stochastic optimization. Retrieved January 30, 2017 from https://arxiv.org/pdf/1412.6980.pdf

[21]

Wu Y, Schuster M, Chen Z, et al. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. Retrieved October 08, 2016 from https://arxiv.org/pdf/1609.08144.pdf

Cited By

Wu T(2021)Modeling The Dynamic Note-Taking Behavior of MOOC Video Learners via Representation Learning2021 IEEE 3rd International Conference on Computer Science and Educational Informatization (CSEI)10.1109/CSEI51395.2021.9477647(291-295)Online publication date: 18-Jun-2021
https://doi.org/10.1109/CSEI51395.2021.9477647

Index Terms

Chinese Live-streaming Barrage Chatbot Combined with User Vectors
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
      1. Natural language generation

Recommendations

Impact of representation of hydraulic structures in modelling a Severn barrage

In this study, enhancements to the numerical representation of sluice gates and turbines were made to the hydro-environmental model Environmental Fluid Dynamics Code (EFDC), and applied to the Severn Tidal Power Group Cardiff-Weston Barrage.The extended ...
Comparison of hydro-environmental impacts for ebb-only and two-way generation for a Severn Barrage

Marine renewable energy is playing an increasing significant role in many parts of the world, mainly due to a rise in the awareness of climate change, and its detrimental effects, and the increasing cost of natural resources. The Severn Estuary, located ...
Study on Biological Nnitrogen Removal in a Combined A/O Biofilm Reactor
ICEET '09: Proceedings of the 2009 International Conference on Energy and Environment Technology - Volume 02

A combined A/O biofilm reactor was designed to treat domestic wastewater. The effect of hydraulic retention time (HRT), dissolved oxygen (DO) and nitrifying fluid return ratio on the nitrogen removal was investigated. The experimental results were as ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

CCEAI '21: Proceedings of the 5th International Conference on Control Engineering and Artificial Intelligence

January 2021

165 pages

ISBN:9781450388870

DOI:10.1145/3448218

Editor:
Dan Zhang

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 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]

In-Cooperation

York University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 February 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

CCEAI 2021

CCEAI 2021: 5th International Conference on Control Engineering and Artificial Intelligence

January 14 - 16, 2021

Sanya, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
113
Total Downloads

Downloads (Last 12 months)16
Downloads (Last 6 weeks)2

Reflects downloads up to 21 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wu T(2021)Modeling The Dynamic Note-Taking Behavior of MOOC Video Learners via Representation Learning2021 IEEE 3rd International Conference on Computer Science and Educational Informatization (CSEI)10.1109/CSEI51395.2021.9477647(291-295)Online publication date: 18-Jun-2021
https://doi.org/10.1109/CSEI51395.2021.9477647

View Options

Get Access

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.

Media

Figures

Other

Tables

View Table of Contents