Towards Two-Way Interaction with Reading Machines

  • Sebastian RiedelEmail author
  • Sameer Singh
  • Guillaume Bouchard
  • Tim Rocktäschel
  • Ivan Sanchez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9449)


As machine learning models that underlie machine reading systems are becoming more complex, latent, and end-to-end, they are also becoming less interpretable and controllable. In times of rule-based systems users could interact with a system in a two-way fashion: injecting their own background knowledge into the system through explanations in the form of rules, and extracting explanations from the system in the form of derivations. It is not clear how this type of communication can be realized within more modern architectures. In this position paper we propose a research agenda that will (re-)enable this two-way communication with machine readers while maintaining the benefits of the models of today. In fact, we argue for a paradigm in which the machine reading system is an agent that communicates with us, learning from our examples and explanations, and providing us with explanations for its decisions we can use to debug and improve the agent further.


Machine Translation Stochastic Gradient Descent Bleu Score Reading Machine Supervise Learning Problem 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work was supported in part by Microsoft Research through its PhD Scholarship Programme, in part by CONAYCT, in part by the TerraSwarm Research Center, one of six centers supported by the STARnet phase of the Focus Center Research Program (FCRP) a Semiconductor Research Corporation program sponsored by MARCO and DARPA, in part by an ARO grant number W911NF-13-1-0246, and in part by the Paul Allen Foundation through an Allen Distinguished Investigator grant.


  1. 1.
    Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: Association for Computational Linguistics (ACL) (2014)Google Scholar
  2. 2.
    Chiticariu, L., Li, Y., Reiss, F.R.: Rule-based information extraction is dead! long live rule-based information extraction systems! In: EMNLP, pp. 827–832, ACL (2013).
  3. 3.
    Craven, M.W., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Advances in Neural Information Processing Systems (NIPS-8), pp. 24–30 (1996)Google Scholar
  4. 4.
    Culotta, A., Sorensen, J.: Dependency tree kernels for relation extraction. In: Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL 2004), Barcelona, Spain (2004).
  5. 5.
    Ganchev, K., Graca, J., Gillenwater, J., Taskar, B.: Posterior regularization for structured latent variable models. Technical report MS-CIS-09-16, University of Pennsylvania Department of Computer and Information Science (2009)Google Scholar
  6. 6.
    Gardner, M., Talukdar, P., Krishnamurthy, J., Mitchell, T.: Incorporating vector space similarity in random walk inference over knowledge bases. In: Proceedings of EMNLP (2014)Google Scholar
  7. 7.
    Mann, G.S., McCallum, A.: Generalized expectation criteria for semi-supervised learning of conditional random fields. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 870–878 (2008)Google Scholar
  8. 8.
    Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL 2009), pp. 1003–1011. Association for Computational Linguistics (2009)Google Scholar
  9. 9.
    Neelakantan, A., Roth, B., McCallum, A.: Compositional vector space models for knowledge base completion. In: Association for Computational Linguistics (ACL) (2015)Google Scholar
  10. 10.
    Reddy, S., Lapata, M., Steedman, M.: Large-scale semantic parsing without question-answer pairs. Trans. Assoc. Comput. Linguist. (TACL) 2, 377–392 (2014)Google Scholar
  11. 11.
    Riedel, S., Yao, L., Marlin, B.M., McCallum, A.: Relation extraction with matrix factorization and universal schemas. In: Joint Human Language Technology Conference/Annual Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2013), June 2013Google Scholar
  12. 12.
    Rocktäschel, T., Singh, S., Riedel, S.: Injecting logical background knowledge into embeddings for relation extraction. In: Proceedings of the 2015 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (2015)Google Scholar
  13. 13.
    Sanchez, I., Rocktaschel, T., Riedel, S., Singh, S.: Towards extracting faithful and descriptive representations of latent variable models. In: AAAI Spring Symposium on Knowledge Representation and Reasoning, March 2015Google Scholar
  14. 14.
    Singh, S., Hillard, D., Leggetter, C.: Minimally-supervised extraction of entities from text advertisements. In: North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT) (2010)Google Scholar
  15. 15.
    Socher, R., Chen, D., Manning, C.D., Ng, A.: Reasoning with neural tensor networks for knowledge base completion. In: Advances in Neural Information Processing Systems, pp. 926–934 (2013)Google Scholar
  16. 16.
    Suchanek, F., Fan, J., Hoffmann, R., Riedel, S., Talukdar, P.P.: Advances in automated knowledge base construction. In: SIGMOD Records Journal, March 2013.
  17. 17.
    Thrun, S.: Extracting rules from artificial neural networks with distributed representations. In: Advances in Neural Information Processing Systems, pp. 505–512 (1995)Google Scholar
  18. 18.
    Toutanova, K., Chen, D., Pantel, P., Poon, H., Choudhury, P., Gamon, M.: Representing text for joint embedding of text and knowledge bases. In: ACL Association for Computational Linguistics, September 2015.
  19. 19.
    Weston, J., Chopra, S., Bordes, A.: Memory networks. CoRR abs/1410.3916 (2014).
  20. 20.
    Zettlemoyer, L.S., Collins, M.: Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars. In: Uncertainty in Artifical Intelligence (UAI) (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Sebastian Riedel
    • 1
    Email author
  • Sameer Singh
    • 2
  • Guillaume Bouchard
    • 1
  • Tim Rocktäschel
    • 1
  • Ivan Sanchez
    • 1
  1. 1.Department of Computer ScienceUniversity College LondonLondonUK
  2. 2.Computer Science & EngineeringUniversity of WashingtonSeattleUSA

Personalised recommendations