Improving Semantic Parsing via Answer Type Inference

In this work, we show the possibility of inferring the answer type before solving a factoid question and leveraging the type information to improve semantic parsing. By replacing the topic entity in a question with its type, we are able to generate an abstract form of the question, whose answer corresponds to the answer type of the original question. A bidirectional LSTM model is built to train over the abstract form of questions and infer their answer types. It is also observed that if we convert a question into a statement form, our LSTM model achieves better accuracy. Using the predicted type information to rerank the logical forms returned by AgendaIL, one of the leading semantic parsers, we are able to improve the F1-score from 49.7% to 52.6% on the WEBQUESTIONS data.

[1]  Mark Steedman,et al.  Transforming Dependency Structures to Logical Forms for Semantic Parsing , 2016, TACL.

[2]  Jonathan Berant,et al.  Semantic Parsing via Paraphrasing , 2014, ACL.

[3]  Xuchen Yao,et al.  Lean Question Answering over Freebase from Scratch , 2015, NAACL.

[4]  Eunsol Choi,et al.  Scaling Semantic Parsers with On-the-Fly Ontology Matching , 2013, EMNLP.

[5]  Estevam R. Hruschka,et al.  Coupled semi-supervised learning for information extraction , 2010, WSDM '10.

[6]  Andrew McCallum,et al.  Unsupervised Relation Discovery with Sense Disambiguation , 2012, ACL.

[7]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[8]  Dongyan Zhao,et al.  Question Answering on Freebase via Relation Extraction and Textual Evidence , 2016, ACL.

[9]  Xuchen Yao,et al.  Information Extraction over Structured Data: Question Answering with Freebase , 2014, ACL.

[10]  Hannah Bast,et al.  More Accurate Question Answering on Freebase , 2015, CIKM.

[11]  Tiejun Zhao,et al.  Knowledge-Based Question Answering as Machine Translation , 2014, ACL.

[12]  Siddharth Patwardhan,et al.  Question analysis: How Watson reads a clue , 2012, IBM J. Res. Dev..

[13]  Hae-Chang Rim,et al.  Joint Relational Embeddings for Knowledge-based Question Answering , 2014, EMNLP.

[14]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[15]  Ming-Wei Chang,et al.  Open Domain Question Answering via Semantic Enrichment , 2015, WWW.

[16]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

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

[18]  Mudhakar Srivatsa,et al.  Exploiting Relevance Feedback in Knowledge Graph Search , 2015, KDD.

[19]  Hong Sun,et al.  A Hybrid Neural Model for Type Classification of Entity Mentions , 2015, IJCAI.

[20]  Krisztian Balog,et al.  Hierarchical target type identification for entity-oriented queries , 2012, CIKM.

[21]  Christopher Potts,et al.  The Life and Death of Discourse Entities: Identifying Singleton Mentions , 2013, NAACL.

[22]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[23]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[24]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[25]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

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

[27]  Jonathan Berant,et al.  Imitation Learning of Agenda-based Semantic Parsers , 2015, TACL.

[28]  Jason Weston,et al.  Large-scale Simple Question Answering with Memory Networks , 2015, ArXiv.

[29]  Oren Etzioni,et al.  No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities , 2012, EMNLP.

[30]  Ming Zhou,et al.  Question Answering over Freebase with Multi-Column Convolutional Neural Networks , 2015, ACL.

[31]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[32]  Dan Roth,et al.  Learning Question Classifiers , 2002, COLING.