Abstract
Question answering (QA) is a very important, but not yet completely resolved problem in artificial intelligence. Solving the QA problem consists of two major steps: relevant fact selection and answering the question. Existing methods usually combine the two steps to solve the problem. A major technique is to add a memory component to infer answers from the chaining facts. It is not very clear how irrelevant facts affect the effectiveness of these methods. In this paper, we propose to separate the two steps and only consider the problem of relevant fact selection. We used a graphical probabilistic model Conditional Random Field (CRF) to model the interdependent relationship among the chaining facts in order to select the relevant ones. In our experiments on a benchmark dataset, we are able to select correctly all relevant facts from 13 tasks out of 19 tasks (F-scores of the rest of the 6 tasks range from 0.8 to 0.97). We also show that using our selector to pre-select relevant facts can substantially improve the accuracies of existing QA systems (e.g. MemN2N (from 88% to 94%) and LSTM (from 66% to 91%) in 13 tasks with complete information).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
In the bAbI dataset, the number of words is limited (less than 200 in one task) such that we just use an integer to represent the word ID in our experiment. Some complex word representation technics such as word embedding can be utilized when the number of words in the corpus increases.
- 2.
Any noun in q, normally, the meaning of sentences carried by the nouns in the sentences.
- 3.
The experiments are based on the public source code https://github.com/facebook/MemNN.
- 4.
The experiments are based on the public source code https://github.com/fchollet/keras.
References
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
Iyyer, M., Boyd-Graber, J.L., Claudino, L.M.B., Socher, R., Daumé III, H.: A neural network for factoid question answering over paragraphs. In: EMNLP, pp. 633–644 (2014)
Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: Proceedings of the 32nd International Conference on Machine Learning (ICML-15), pp. 2342–2350 (2015)
Kumar, A., Irsoy, O., Su, J., Bradbury, J., English, R., Pierce, B., Ondruska, P., Gulrajani, I., Socher, R.: Ask me anything: dynamic memory networks for natural language processing. CoRR, abs/1506.07285 (2015)
Lin, D., Pantel, P.: Discovery of inference rules for question-answering. Nat. Lang. Eng. 7(04), 343–360 (2001)
Mikolov, T., Karafiát, M., Burget, L., Cernockỳ, J., Khudanpur, S.: Recurrent neural network based language model. In: Interspeech, vol. 2, p. 3 (2010)
Peng, B., Lu, Z., Li, H., Wong, K.F.: Towards neural network-based reasoning. arXiv preprint arXiv:1508.05508 (2015)
Qiu, X., Huang, X.: Convolutional neural tensor network architecture for community-based question answering. In: IJCAI, pp. 1305–1311 (2015)
Ravichandran, D., Hovy, E.: Learning surface text patterns for a question answering system. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 41–47. Association for Computational Linguistics (2002)
Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Advances in neural information processing systems, pp. 2440–2448 (2015)
Sundermeyer, M., Schlüter, R., Ney, H.: LSTM neural networks for language modeling. In: Interspeech, pp. 194–197 (2012)
Sutton, C., McCallum, A.: An introduction to conditional random fields for relational learning. Introduction to statistical relational learning, pp. 93–128 (2006)
Tu, W., Cheung, D.W.L., Mamoulis, N., Yang, M., Lu, Z.: Real-time detection and sorting of news on microblogging platforms. In: PACLIC (2015)
Weston, J., Bordes, A., Chopra, S., Rush, A.M., van Merriënboer, B., Joulin, A., Mikolov, T.: Towards AI-complete question answering: a set of prerequisite toy tasks. arXiv preprint arXiv:1502.05698 (2015)
Weston, J., Chopra, S., Bordes, A.: Memory networks. arXiv preprint arXiv:1410.3916 (2014)
Wu, H., Wu, W., Zhou, M., Chen, E., Duan, L., Shum, H.Y.: Improving search relevance for short queries in community question answering. In: Proceedings of the 7th ACM International Conference on Web Search and Data Mining, pp. 43–52. ACM (2014)
Yang, M., Chow, K.-P.: An Information Extraction Framework for Digital Forensic Investigations. In: Peterson, G., Shenoi, S. (eds.) DigitalForensics 2015. IAICT, vol. 462, pp. 61–76. Springer, Cham (2015). doi:10.1007/978-3-319-24123-4_4
Yang, M., Tu, W., Yin, W., Lu, Z.: Deep Markov neural network for sequential data classification. In: The 53rd Annual Meeting of the Association for Computational Linguistics. ACL (2015)
Zhang, K., Wu, W., Wu, H., Li, Z., Zhou, M.: Question retrieval with high quality answers in community question answering. In: Proceedings of the 23rd ACM International Conference on Information and Knowledge Management, pp. 371–380. ACM (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Liang, Y., Zhu, J., Li, Y., Yang, M., Yiu, S.M. (2017). Relevant Fact Selection for QA via Sequence Labeling. In: Li, G., Ge, Y., Zhang, Z., Jin, Z., Blumenstein, M. (eds) Knowledge Science, Engineering and Management. KSEM 2017. Lecture Notes in Computer Science(), vol 10412. Springer, Cham. https://doi.org/10.1007/978-3-319-63558-3_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-63558-3_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63557-6
Online ISBN: 978-3-319-63558-3
eBook Packages: Computer ScienceComputer Science (R0)