Abstract
Complex question answering, the task of answering complex natural language questions that rely on inference, requires the aggregation of information from multiple sources. Automatic aggregation often fails because it combines semantically unrelated facts leading to bad inferences. This paper proposes methods to address this inference drift problem. In particular, the paper develops unsupervised and supervised mechanisms to control random walks on Open Information Extraction (OIE) knowledge graphs. Empirical evaluation on an elementary science exam benchmark shows that the proposed methods enables effective aggregation even over larger graphs and demonstrates the complementary value of information aggregation for answering complex questions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This is inspired by the work of Gao et al. (2011), who use a linear parametrization but for a single graph problem using a different modeling approach.
- 2.
QI denotes edge between Question and Intermediate Node.
- 3.
References
Etzioni, O.: Search needs a shake-up. Nature 476(7358), 25–26 (2011)
Clark, P., Harrison, P., Balasubramanian, N.: A study of the knowledge base requirements for passing an elementary science test. In: AKBC@CIKM (2013)
Clark, P., Etzioni, O.: My computer is an honor student - but how intelligent is it? Standardized tests as a measure of AI. AI Mag. 37, 5–12 (2016)
Jansen, P., Balasubramanian, N., Surdeanu, M., Clark, P.: What’s in an explanation? Characterizing knowledge and inference requirements for elementary science exams. In: COLING (2016)
Mausam, Schmitz, M., Soderland, S., Bart, R., Etzioni, O.: Open language learning for information extraction. In: EMNLP-CoNLL (2012)
Khot, T., Sabharwal, A., Clark, P.: Answering complex questions using open information extraction. CoRR, abs/1704.05572 (2017)
Khashabi, D., Sabharwal, T.K.A., Roth, D.: Learning what is essential in questions. In: COLING (2017)
Haveliwala, T.H.: Topic-sensitive pagerank. In: WWW (2002)
Jansen, P., Sharp, R., Surdeanu, M., Clark, P.: Framing QA as building and ranking intersentence answer justifications. In: Computational Linguistics (2017)
Gao, B., Liu, T.-Y., Wei, W., Wang, T., Li, H.: Semi-supervised ranking on very large graphs with rich metadata. In: ACM SIGKDD, pp. 96–104 (2011)
Rocchio, J.J.: Relevance feedback in information retrieval. In: Salton: The SMART Retrieval System: Experiments in Automatic Document Processing (1971)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Khot, T., Balasubramanian, N., Gribkoff, E., Sabharwal, A., Clark, P., Etzioni, O.: Exploring Markov logic networks for question answering. In: EMNLP (2015)
Clark, P., Etzioni, O., Khot, T., Sabharwal, A., Tafjord, O., Turney, P.D., Khashabi, D.: Combining retrieval, statistics, and inference to answer elementary science questions. In: AAAI (2016)
Sharp, R., Jansen, P., Surdeanu, M., Clark, P.: Spinning straw into gold: using free text to train monolingual alignment models for non-factoid question answering. In: HLT-NAACL (2015)
Fried, D., Jansen, P., Hahn-Powell, G., Surdeanu, M., Clark, P.: Higher-order lexical semantic models for non-factoid answer reranking. Trans. Assoc. Comput. Linguist. 3, 197–210 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Kwon, H., Trivedi, H., Jansen, P., Surdeanu, M., Balasubramanian, N. (2018). Controlling Information Aggregation for Complex Question Answering. In: Pasi, G., Piwowarski, B., Azzopardi, L., Hanbury, A. (eds) Advances in Information Retrieval. ECIR 2018. Lecture Notes in Computer Science(), vol 10772. Springer, Cham. https://doi.org/10.1007/978-3-319-76941-7_72
Download citation
DOI: https://doi.org/10.1007/978-3-319-76941-7_72
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-76940-0
Online ISBN: 978-3-319-76941-7
eBook Packages: Computer ScienceComputer Science (R0)