Advertisement

CI-Bot: A Hybrid Chatbot Enhanced by Crowdsourcing

  • Xulei Liang
  • Rong Ding
  • Mengxiang LinEmail author
  • Lei Li
  • Xingchi Li
  • Song Lu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10612)

Abstract

Question and answer website is an effective way for people to get information from others. Recently, chatbot has been more and more widely used. In this paper, we propose CI-Bot, a Crowd-Intelligence-chatBot. CI-Bot is a hybrid intelligent chatbot, in which crowdsourcing is introduced on the basis of a chatbot. When receiving a problem, the conversational partner of CI-Bot first tries to solve it automatically. If the question is beyond the knowledge of CI-Bot, expert recommender would find out experts it knows and consults them. Ultimately, the problem would be solved and the answers generated by the experts are added to a corpus, to increase the ability of CI-Bot. We implemented a prototype on the top of Hubot and Wechat. The preliminary experiment results validate the effectiveness of CI-Bot.

References

  1. 1.
    Li, W., Wu, W., Wang, H., Cheng, X., Chen, H., Zhou, Z., Ding, R.: Crowd intelligence in AI 2.0 era. Front. Inf. Technol. Electron. Eng. 18, 15–43 (2017)CrossRefGoogle Scholar
  2. 2.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)Google Scholar
  3. 3.
    Ji, Z., Lu, Z., Li, H.: An information retrieval approach to short text conversation. arXiv preprint. arXiv:1408.6988 (2014)
  4. 4.
    Goldberg, Y., Levy, O.: word2vec explained: deriving Mikolov et al.’s negative-sampling word-embedding method. arXiv preprint. arXiv:1402.3722 (2014)
  5. 5.
    Franklin, M.J., Kossmann, D., Kraska, T., Ramesh, S., Xin, R.: CrowdDB: answering queries with crowdsourcing. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data. ACM, pp. 61–72 (2011)Google Scholar
  6. 6.
    Merritt, D., Jones, J., Ackerman, M.S., Lasecki, W.S.: Kurator: using the crowd to help families with personal curation tasks (2017)Google Scholar
  7. 7.
    Savenkov, D., Weitzner, S., Agichtein, E.: Crowdsourcing for (almost) real-time question answering. In: Workshop on Human-Computer Question Answering, NAACL (2016)Google Scholar
  8. 8.
    Jeong, J.W., Morris, M.R., Teevan, J., Liebling, D.J.: A crowd-powered socially embedded search engine. In: ICWSM (2013)Google Scholar
  9. 9.
    Huang, T.H.K., Lasecki, W.S., Azaria, A., Bigham, J.P.: “Is there anything else I can help you with?” challenges in deploying an on-demand crowd-powered conversational agent. In: Fourth AAAI Conference on Human Computation and Crowdsourcing (2016)Google Scholar
  10. 10.
    Williams, J.J., Kim, J., Rafferty, A., Maldonado, S., Gajos, K.Z., Lasecki, W.S., Heffernan, N.: Axis: Generating explanations at scale with learnersourcing and machine learning. In: Proceedings of the Third ACM Conference on Learning@ Scale. ACM pp. 379–388 (2016)Google Scholar
  11. 11.
    Huang, T.H.K., Lasecki, W.S., Bigham, J.P.: Guardian: a crowd-powered spoken dialog system for web APIs. In: Third AAAI conference on human computation and crowdsourcing (2015)Google Scholar
  12. 12.
    Tong, Y., She, J., Ding, B., Chen, L., Wo, T., Xu, K.: Online minimum matching in real-time spatial data: experiments and analysis. Proc. VLDB Endow. 9, 1053–1064 (2016)CrossRefGoogle Scholar
  13. 13.
    Tong, Y., She, J., Ding, B., Wang, L., Chen, L.: Online mobile micro-task allocation in spatial crowdsourcing. In: Proceedings of the 32nd International Conference on Data Engineering, pp. 49–60 (2016)Google Scholar
  14. 14.
    Tong, Y., Wang, L., Zhou, Z., Ding, B., Chen, L., Ye, J., Xu, K.: Flexible online task assignment in real-time spatial data. Proc. VLDB Endow. 10, 1334–1345 (2017)CrossRefGoogle Scholar
  15. 15.
    Bigham, J.P., Jayant, C., Ji, H., Little, G., Miller, A., Miller, R.C., Miller, R., Tatarowicz, A., White, B., White, S., et al.: Vizwiz: nearly real-time answers to visual questions. In: Proceedings of the 23nd Annual ACM Symposium on User Interface Software and Technology. ACM, pp. 333–342 (2010)Google Scholar
  16. 16.
    Lasecki, W.S., Miller, C.D., Naim, I., Kushalnagar, R., Sadilek, A., Gildea, D., Bigham, J.P.: Scribe: deep integration of human and machine intelligence to caption speech in real time. Commun. ACM 60 (2017)Google Scholar
  17. 17.
    Yang, L., Qiu, M., Gottipati, S., Zhu, F., Jiang, J., Sun, H., Chen, Z.: CQArank: jointly model topics and expertise in community question answering. In: Proceedings of the 22nd ACM International Conference on Information and Knowledge Management. ACM, pp. 99–108 (2013)Google Scholar
  18. 18.
    Kittur, A., Nickerson, J.V., Bernstein, M., Gerber, E., Shaw, A., Zimmerman, J., Lease, M., Horton, J.: The future of crowd work. In: Proceedings of the 2013 Conference on Computer Supported Cooperative Work. ACM pp. 1301–1318 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Xulei Liang
    • 1
  • Rong Ding
    • 1
  • Mengxiang Lin
    • 1
    Email author
  • Lei Li
    • 1
  • Xingchi Li
    • 1
  • Song Lu
    • 1
  1. 1.State Key Laboratory of Software Development EnvironmentBeihang UniversityBeijingChina

Personalised recommendations