Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
arXiv (Cornell University)Published 4 July 2012Open access
Luke Zettlemoyer, Michael J. Collins
Citations791
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
This paper addresses the problem of mapping natural language sentences to lambda-calculus encodings of their meaning. We describe a learning algorithm that takes as input a training set of sentences labeled with expressions in the lambda calculus. The algorithm induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. We apply the method to the task of learning natural language interfaces to databases and show that the learned parsers outperform previous methods in two benchmark database domains.
Keywords
Computer Science
Proceedings of the IEEEGradient-based learning applied to document recognition
58,219 Citations1998Yann LeCun, Léon Bottou +2 more
This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
ScholarlyCommons (University of Pennsylvania)Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
12,978 Citations2001John Lafferty, Andrew McCallum +1 more
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Foundations of statistical natural language processing
9,996 Citations1999Christopher D. Manning, Hinrich Schütze
The MIT Press eBooksThe Syntactic Process
1,610 Citations2000Mark Steedman
The book covers topics in formal linguistics, intonational phonology, computational linguistics and experimental psycholinguistics, presenting them as an integrated theory of the language faculty in a form accessible to readers from any of those fields.
Max-Margin Markov Networks
1,251 Citations2003Ben Taskar, Carlos Guestrin +1 more
Maximum margin Markov (M3) networks incorporate both kernels, which efficiently deal with high-dimensional features, and the ability to capture correlations in structured data, and a new theoretical bound for generalization in structured domains is provided.
Natural Language EngineeringNatural language interfaces to databases – an introduction
741 Citations1995Ion Androutsopoulos, Graéme Ritchie +1 more
An introduction to natural language interfaces to databases (NLIDBS) and some less explored areas of NLIDB research are presented, namely database updates, meta-knowledge questions, temporal questions, and multi-modal NLIDBS.
Learning to parse database queries using inductive logic programming
682 Citations1996John M. Zelle, Raymond J. Mooney
Experimental results with a complete database-query application for U.S. geography show that CHILL is able to learn parsers that outperform a preexisting, hand-crafted counterpart, and provide direct evidence of the utility of an empirical approach at the level of a complete natural language application.
The Journal of the Acoustical Society of AmericaTrainable grammars for speech recognition
538 Citations1979James K. Baker
This paper presents a generalization of these algorithms to certain denumerable‐state, hidden Markov processes that permits automatic training of the stochastic analog of an arbitrary context free grammar.
Medical Entomology and ZoologySurface Structure and Interpretation
536 Citations1996Mark Steedman
The core of the book is a detailed treatment of extraction, a focus of syntactic research since the early work of Chomsky and Ross, and relates CCG to other categorial and type-driven approaches and to proposals for minimalism in linguistic theory.
Lecture notes in computer scienceUsing Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing
268 Citations2001Lappoon R. Tang, Raymond J. Mooney
Preliminary results demonstrated that an approach which combines different learning methods in inductive logic programming (ILP) to allow a learner to produce more expressive hypotheses than that of each individual learner is promising.
The MIT Press eBooksType-Logical Semantics
250 Citations1998Bob Carpenter
Simply typed lambda-calculus higher-order logic applicative categorial grammar the Lambek calculus coordination and unbounded dependencies quantifiers and scope plurals pronouns and dependency modal logic intentionality tense and aspect.
Wide-coverage semantic representations from a CCG parser
207 Citations2004Johan Bos, Stephen Clark +3 more
It is demonstrated that well-formed semantic representations can be produced for over 97% of the sentences in unseen WSJ text, a major step towards widecoverage semantic interpretation, one of the key objectives of the field of NLP.
Empirical Methods in Natural Language ProcessingMax-Margin Parsing
198 Citations2004Ben Taskar, Dan Klein +3 more
A novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines is presented, which allows one to efficiently learn a model which discriminates among the entire space of parse trees, as opposed to reranking the top few candidates.
Modern natural language interfaces to databases
195 Citations2004Ana-Maria Popescu, Alex Armanasu +3 more
The paper shows how a strong semantic model coupled with "light re-training" enables PRECISE to overcome parser errors, and correctly map from parsed questions to the corresponding SQL queries.
Estimators for stochastic "Unification-Based" grammars
168 Citations1999Mark Johnson, Stuart Geman +3 more
Two computationally-tractable ways of estimating the parameters of Stochastic "Unification-Based" Grammars from a training corpus of syntactic analyses are described and applied to estimate a stochastic version of Lexical-Functional Grammar.
A fully statistical approach to natural language interfaces
143 Citations1996S.L. Miller, David Stallard +2 more
This work presents a natural language interface system which is based entirely on trained statistical models, resulting in an end-to-end system that maps input utterances into meaning representation frames.
Computer Speech & LanguageSemantic processing using the Hidden Vector State model
131 Citations2004Yulan He, Steve Young
When measured by its ability to extract attribute-value pairs from natural language queries in the travel domain, the HVS model outperforms a conventional finite-state semantic tagger by 4.1% in F-measure for ATIS and by 6.6% for Communicator, suggesting that the benefit of the H VS model's ability to encode context increases as the task becomes more complex.
Log-linear models for wide-coverage CCG parsing
72 Citations2003Stephen Clark, James Curran
This paper describes log-linear parsing models for Combinatory Categorial Grammar and describes a parellelised implementation which runs on a Beowulf cluster and allows the complete WSJ Penn Treebank to be used for estimation.
Journal of Artificial Intelligence ResearchAcquiring Word-Meaning Mappings for Natural Language Interfaces
67 Citations2003Cynthia A. Thompson
It is shown that active learning can significantly reduce the number of annotated examples required to achieve a given level of performance, and is applied to semantic lexicons.
Unsupervised Lexical Learning with Categorial Grammars using the LLL Corpus
7 Citations1999Stephen Watkinson, Suresh Manandhar