Tables as Semi-structured Knowledge for Question Answering

Question answering requires access to a knowledge base to check facts and reason about information. Knowledge in the form of natural language text is easy to acquire, but difficult for automated reasoning. Highly-structured knowledge bases can facilitate reasoning, but are difficult to acquire. In this paper we explore tables as a semi-structured formalism that provides a balanced compromise to this trade-off. We first use the structure of tables to guide the construction of a dataset of over 9000 multiple-choice questions with rich alignment annotations, easily and efficiently via crowd-sourcing. We then use this annotated data to train a semi-structured feature-driven model for question answering that uses tables as a knowledge base. In benchmark evaluations, we significantly outperform both a strong unstructured retrieval baseline and a highly structured Markov Logic Network model.

[1]  Peter Clark.  Elementary School Science and Math Tests as a Driver for AI: Take the Aristo Challenge! , 2015, AAAI.

[2]  Jayant Madhavan,et al.  Recovering Semantics of Tables on the Web , 2011, Proc. VLDB Endow..

[3]  Sanda M. Harabagiu,et al.  Question Answering Based on Semantic Structures , 2004, COLING.

[4]  Quoc V. Le,et al.  Neural Programmer: Inducing Latent Programs with Gradient Descent , 2015, ICLR.

[5]  Hang Li,et al.  Neural Enquirer: Learning to Query Tables , 2015, ArXiv.

[6]  Tim Finin,et al.  Exploiting a Web of Semantic Data for Interpreting Tables , 2010 .

[7]  Daisy Zhe Wang,et al.  WebTables: exploring the power of tables on the web , 2008, Proc. VLDB Endow..

[8]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[9]  Mirella Lapata,et al.  Using Semantic Roles to Improve Question Answering , 2007, EMNLP.

[10]  Chris Callison-Burch,et al.  PPDB: The Paraphrase Database , 2013, NAACL.

[11]  Oren Etzioni,et al.  Exploring Markov Logic Networks for Question Answering , 2015, EMNLP.

[12]  Patrick Pantel,et al.  Discovery of inference rules for question-answering , 2001, Natural Language Engineering.

[13]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[14]  Percy Liang,et al.  Compositional Semantic Parsing on Semi-Structured Tables , 2015, ACL.

[15]  Hao Ma,et al.  Table Cell Search for Question Answering , 2016, WWW.

[16]  Oren Etzioni,et al.  Open question answering over curated and extracted knowledge bases , 2014, KDD.

[17]  Ming Zhou,et al.  Answering Questions with Complex Semantic Constraints on Open Knowledge Bases , 2015, CIKM.

[18]  Sunita Sarawagi,et al.  Answering Table Queries on the Web using Column Keywords , 2012, Proc. VLDB Endow..

[19]  Jimmy J. Lin,et al.  Quantitative evaluation of passage retrieval algorithms for question answering , 2003, SIGIR.

[20]  Sanda M. Harabagiu,et al.  COGEX: A Logic Prover for Question Answering , 2003, NAACL.

[21]  Murat Demirbas,et al.  Crowdsourcing for Multiple-Choice Question Answering , 2014, AAAI.

[22]  Oren Etzioni,et al.  Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions , 2016, AAAI.

[23]  Wei Li,et al.  Information Extraction Supported Question Answering , 1999, TREC.

[24]  Heng Ji,et al.  Knowledge Base Population: Successful Approaches and Challenges , 2011, ACL.