arXiv (Cornell University) · 2017 · 12 citations · 16 references
ComputingComputer ScienceDatabasesMachine LearningNatural Language ProcessingAnnotationCorpus AnnotationLanguage ModelingMachine TranslationNatural Language GenerationNatural Language UnderstandingCorpus CreationData-driven Machine TranslationNatural Language InterfacesNatural User InterfacesNeural Language ModelsPortabilitySequence-to-sequence RecognitionTranslation Problem Solving
Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouraging baseline results on a smaller manually annotated test corpus, obtained using an attention-based sequence-to-sequence neural network.
16
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
The Stanford CoreNLP Natural Language Processing Toolkit
Christopher D. Manning, Mihai Surdeanu, John Bauer et al. · 2014 · 7.2K citations · Full text
Semantic Parsing on Freebase from Question-Answer Pairs
Jonathan Berant, Andrew Chou, Roy Frostig et al. · 2013 · 1.6K citations · Full text