Key-Value Memory Networks for Directly Reading Documents

Directly reading documents and being able to answer questions from them is an unsolved challenge. To avoid its inherent difficulty, question answering (QA) has been directed towards using Knowledge Bases (KBs) instead, which has proven effective. Unfortunately KBs often suffer from being too restrictive, as the schema cannot support certain types of answers, and too sparse, e.g. Wikipedia contains much more information than Freebase. In this work we introduce a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation. To compare using KBs, information extraction or Wikipedia documents directly in a single framework we construct an analysis tool, WikiMovies, a QA dataset that contains raw text alongside a preprocessed KB, in the domain of movies. Our method reduces the gap between all three settings. It also achieves state-of-the-art results on the existing WikiQA benchmark.

[1]  Wenpeng Yin,et al.  Convolutional Neural Network for Paraphrase Identification , 2015, NAACL.

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

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

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

[5]  Zhiguo Wang,et al.  Sentence Similarity Learning by Lexical Decomposition and Composition , 2016, COLING.

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

[7]  Yi Yang,et al.  WikiQA: A Challenge Dataset for Open-Domain Question Answering , 2015, EMNLP.

[8]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

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

[10]  Ellen M. Voorhees,et al.  The TREC-8 Question Answering Track Report , 1999, TREC.

[11]  Estevam R. Hruschka,et al.  Toward an Architecture for Never-Ending Language Learning , 2010, AAAI.

[12]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[13]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

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

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

[16]  Noah A. Smith,et al.  What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA , 2007, EMNLP.

[17]  Bowen Zhou,et al.  Attentive Pooling Networks , 2016, ArXiv.

[18]  Wen-tau Yih,et al.  Web-based Question Answering: Revisiting AskMSR , 2015 .

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

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

[21]  Phil Blunsom,et al.  Neural Variational Inference for Text Processing , 2015, ICML.

[22]  Jason Weston,et al.  The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations , 2015, ICLR.

[23]  Tom M. Mitchell,et al.  Learning to construct knowledge bases from the World Wide Web , 2000, Artif. Intell..

[24]  Tapani Raiko,et al.  International Conference on Learning Representations (ICLR) , 2016 .

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

[26]  Ellen M. Voorhees,et al.  Building a question answering test collection , 2000, SIGIR '00.

[27]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[28]  Xiang Zhang,et al.  Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems , 2015, ICLR.

[29]  Michele Banko,et al.  AskMSR: Question Answering Using the Worldwide Web , 2002 .

[30]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..