Search-based Neural Structured Learning for Sequential Question Answering

Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans. In an effort to explore a conversational QA setting, we present a more realistic task: answering sequences of simple but inter-related questions. We collect a dataset of 6,066 question sequences that inquire about semi-structured tables from Wikipedia, with 17,553 question-answer pairs in total. To solve this sequential question answering task, we propose a novel dynamic neural semantic parsing framework trained using a weakly supervised reward-guided search. Our model effectively leverages the sequential context to outperform state-of-the-art QA systems that are designed to answer highly complex questions.

[1]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[2]  Ben Taskar,et al.  Max-Margin Markov Networks , 2003, NIPS.

[3]  Sanda M. Harabagiu,et al.  Experiments with Interactive Question-Answering , 2005, ACL.

[4]  Thomas Hofmann,et al.  Large Margin Methods for Structured and Interdependent Output Variables , 2005, J. Mach. Learn. Res..

[5]  John Hale,et al.  Uncertainty About the Rest of the Sentence , 2006, Cogn. Sci..

[6]  Jimmy J. Lin,et al.  Overview of the TREC 2006 ciQA task , 2007, SIGF.

[7]  R. Levy.  Expectation-based syntactic comprehension , 2008, Cognition.

[8]  Luke S. Zettlemoyer,et al.  Learning Context-Dependent Mappings from Sentences to Logical Form , 2009, ACL.

[9]  Luke S. Zettlemoyer,et al.  Bootstrapping Semantic Parsers from Conversations , 2011, EMNLP.

[10]  Stefan L. Frank,et al.  Uncertainty Reduction as a Measure of Cognitive Load in Sentence Comprehension , 2013, Top. Cogn. Sci..

[11]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[12]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

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

[14]  Ming-Wei Chang,et al.  Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base , 2015, ACL.

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

[16]  Percy Liang,et al.  Simpler Context-Dependent Logical Forms via Model Projections , 2016, ACL.

[17]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[18]  Percy Liang,et al.  Learning executable semantic parsers for natural language understanding , 2016, Commun. ACM.

[19]  Ming-Wei Chang,et al.  The Value of Semantic Parse Labeling for Knowledge Base Question Answering , 2016, ACL.

[20]  Peter Norvig,et al.  Deep Learning with Dynamic Computation Graphs , 2017, ICLR.

[21]  Kevin Duh,et al.  DyNet: The Dynamic Neural Network Toolkit , 2017, ArXiv.

[22]  Chen Liang,et al.  Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision , 2016, ACL.

[23]  Ming-Wei Chang,et al.  Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision , 2017, EMNLP.

[24]  Martín Abadi,et al.  Learning a Natural Language Interface with Neural Programmer , 2016, ICLR.