Open Question Answering with Weakly Supervised Embedding Models

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such approaches can be effective but at the cost of either large amounts of human-labeled data or by defining lexicons and grammars tailored by practitioners. In this paper, we instead take the radical approach of learning to map questions to vectorial feature representations. By mapping answers into the same space one can query any knowledge base independent of its schema, without requiring any grammar or lexicon. Our method is trained with a new optimization procedure combining stochastic gradient descent followed by a fine-tuning step using the weak supervision provided by blending automatically and collaboratively generated resources. We empirically demonstrate that our model can capture meaningful signals from its noisy supervision leading to major improvements over paralex, the only existing method able to be trained on similar weakly labeled data.

[1]  Luke S. Zettlemoyer,et al.  Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations , 2011, ACL.

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

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

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

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

[6]  Pavel Rychlý,et al.  Building a 70 billion word corpus of English from ClueWeb , 2012, LREC.

[7]  Ni Lao,et al.  Reading The Web with Learned Syntactic-Semantic Inference Rules , 2012, EMNLP.

[8]  Jason Weston,et al.  Large scale image annotation: learning to rank with joint word-image embeddings , 2010, Machine Learning.

[9]  Jason Weston,et al.  Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction , 2013, EMNLP.

[10]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[11]  Alexander Yates,et al.  Large-scale Semantic Parsing via Schema Matching and Lexicon Extension , 2013, ACL.

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

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

[14]  Daniel Jurafsky,et al.  Distant supervision for relation extraction without labeled data , 2009, ACL.

[15]  Jason Weston,et al.  Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing , 2012, AISTATS.

[16]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[17]  Jens Lehmann,et al.  Template-based question answering over RDF data , 2012, WWW.

[18]  Oren Etzioni,et al.  Paraphrase-Driven Learning for Open Question Answering , 2013, ACL.

[19]  Stephen J. Wright,et al.  Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent , 2011, NIPS.

[20]  Oren Etzioni,et al.  Identifying Relations for Open Information Extraction , 2011, EMNLP.

[21]  Oren Etzioni,et al.  Scaling question answering to the Web , 2001, WWW '01.

[22]  Jimmy J. Lin,et al.  AskMSR: Question Answering Using the Worldwide Web , 2002 .

[23]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[24]  Jens Lehmann,et al.  DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia , 2015, Semantic Web.

[25]  Andrew McCallum,et al.  Relation Extraction with Matrix Factorization and Universal Schemas , 2013, NAACL.

[26]  Gerhard Weikum,et al.  Natural Language Questions for the Web of Data , 2012, EMNLP.