Natural language interfaces to databases-An introduction
TL;DR: This paper is 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.
Abstract: This paper is an introduction to natural language interfaces to databases (NLIDBS). A brief overview of the history of NLIDBS is first given. Some advantages and disadvantages of NLIDBS are then discussed, comparing NLIDBS to formal query languages, form-based interfaces, and graphical interfaces. An introduction to some of the linguistic problems NLIDBS have to confront follows, for the benefit of readers less familiar with computational linguistics. The discussion then moves on to NLIDB architectures, portability issues, restricted natural language input systems (including menu-based NLIDBS), and NLIDBS with reasoning capabilities. Some less explored areas of NLIDB research are then presented, namely database updates, meta-knowledge questions, temporal questions, and multi-modal NLIDBS. The paper ends with reflections on the current state of the art.
Citations
More filters
Book•
12 Jun 2009TL;DR: This book offers a highly accessible introduction to natural language processing, the field that supports a variety of language technologies, from predictive text and email filtering to automatic summarization and translation.
Abstract: This book offers a highly accessible introduction to natural language processing, the field that supports a variety of language technologies, from predictive text and email filtering to automatic summarization and translation. With it, you'll learn how to write Python programs that work with large collections of unstructured text. You'll access richly annotated datasets using a comprehensive range of linguistic data structures, and you'll understand the main algorithms for analyzing the content and structure of written communication. Packed with examples and exercises, Natural Language Processing with Python will help you: Extract information from unstructured text, either to guess the topic or identify "named entities" Analyze linguistic structure in text, including parsing and semantic analysis Access popular linguistic databases, including WordNet and treebanks Integrate techniques drawn from fields as diverse as linguistics and artificial intelligence This book will help you gain practical skills in natural language processing using the Python programming language and the Natural Language Toolkit (NLTK) open source library. If you're interested in developing web applications, analyzing multilingual news sources, or documenting endangered languages -- or if you're simply curious to have a programmer's perspective on how human language works -- you'll find Natural Language Processing with Python both fascinating and immensely useful.
3,361 citations
Proceedings Article•
26 Jul 2005TL;DR: A learning algorithm is described that takes as input a training set of sentences labeled with expressions in the lambda calculus and 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.
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.
865 citations
Cites background from "Natural language interfaces to data..."
...Androutsopoulos, Ritchie, and Thanisch (1995) provide a comprehensive summary of this work....
[...]
Posted Content•
TL;DR: In this paper, a learning algorithm that takes as input a training set of sentences labeled with expressions in the lambda calculus is presented, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence.
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.
662 citations
19 Jun 2011
TL;DR: A new semantic formalism, dependency-based compositional semantics (DCS) is developed and a log-linear distribution over DCS logical forms is defined and it is shown that the system obtains comparable accuracies to even state-of-the-art systems that do require annotated logical forms.
Abstract: Compositional question answering begins by mapping questions to logical forms, but training a semantic parser to perform this mapping typically requires the costly annotation of the target logical forms. In this paper, we learn to map questions to answers via latent logical forms, which are induced automatically from question-answer pairs. In tackling this challenging learning problem, we introduce a new semantic representation which highlights a parallel between dependency syntax and efficient evaluation of logical forms. On two standard semantic parsing benchmarks (Geo and Jobs), our system obtains the highest published accuracies, despite requiring no annotated logical forms.
651 citations
Cites background from "Natural language interfaces to data..."
...nterfaces to databases (NLIDBs) has a long history in NLP, starting from the early days of AI with systems such as Lunar (Woods et al., 1972), Chat-80 (Warren and Pereira, 1982), and many others (see Androutsopoulos et al. (1995) for an overview). While quite successful in their respective limited domains, because these systems were constructed from manually-built rules, they became dicult to scale up, both to other domains ...
[...]
12 Jan 2003
TL;DR: The Precise NLI is introduced, which reduces the semantic interpretation challenge in NLIs to a graph matching problem and shows that Precise has high coverage and accuracy over common English questions.
Abstract: The need for Natural Language Interfaces (NLIs) to databases has become increasingly acute as more nontechnical people access information through their web browsers, PDAs and cell phones. Yet NLIs are only usable if they map natural language questions to SQL queries correctly. We introduce the Precise NLI [2], which reduces the semantic interpretation challenge in NLIs to a graph matching problem. Precise uses the max-flow algorithm to efficiently solve this problem. Each max-flow solution corresponds to a possible semantic interpretation of the sentence. precise collects max-flow solutions, discards the solutions that do not obey syntactic constraints and retains the rest as the basis for generating SQL queries corresponding to the question q. The syntactic information is extracted from the parse tree corresponding to the given question which is computed by a statistical parser [1]. For a broad, well-defined class of semantically tractable natural language questions, Precise is guaranteed to map each question to the corresponding SQL querySemantically tractable questions correspond to a natural, domain-independent subset of English that can be efficiently and accurately interpreted as nonrecursive Datalog clauses. Precise is transportable to arbitrary databases, such as the Restaurants,Jobs and Geography databases used in our implementation. Examples of semantically tractable questions include: "What Chinese restaurants with a 3.5 rating are in Seattle?", "What are the areas of US states with large populations?", "What jobs require 4 years of experience and desire a B.S.CS degree?".Given a question which is not semantically tractable, Precise recognizes it as such and informs the user that it cannot answer it.Given a semantically tractable question, Precise computes the set of non-equivalent SQL interpretations corresponding to the question. If a unique such SQL interpretation exists, Precise outputs it together with the corresponding result set obtained by querying the current database. If the set contains more than one SQL interpretation, the natural language question is ambiguous in the context of the current database. In this case, Precise asks for the user's help in determining which interpretation is the correct one.Our experiments have shown that Precise has high coverage and accuracy over common English questions. In future work, we plan to explore increasingly broad classes of questions and include Precise as a module in a full-fledged dialog system. An important direction for future work is helping users understand the types of questions Precise cannot handle via dialog, enabling them to build an accurate mental model of the system and its capabilities. Also, our own group's work on the EXACT natural language interface [3] builds on Precise and on the underlying theoretical framework. EXACT composes an extended version of Precise with a sound and complete planner to develop a powerful and provably reliable interface to household appliances
552 citations
Cites background from "Natural language interfaces to data..."
...While powerful, these systems don’t offer theoretical guarantees, and are based on very different algorithms.While there has been extensive work on NLIs [ 2 ], most of the earlier work is different from our own....
[...]
...Research on Natural Language Interfaces to databases (NLIs) has largely tapered off since the mid 1980’s [ 2 ].Yet the need for NLIs has become increasingly acute as more and more nontechnical people access a wide range of databases through their web browsers, PDAs, and cell phones (e.g., accessing services such as moviefone and tellme).The tiny screen and keyboard of a cell phone or PDA make interaction paradigms such as direct manipulation ......
[...]
References
More filters
IBM1
TL;DR: In this article, a model based on n-ary relations, a normal form for data base relations, and the concept of a universal data sublanguage are introduced, and certain operations on relations are discussed and applied to the problems of redundancy and consistency in the user's model.
Abstract: Future users of large data banks must be protected from having to know how the data is organized in the machine (the internal representation). A prompting service which supplies such information is not a satisfactory solution. Activities of users at terminals and most application programs should remain unaffected when the internal representation of data is changed and even when some aspects of the external representation are changed. Changes in data representation will often be needed as a result of changes in query, update, and report traffic and natural growth in the types of stored information.Existing noninferential, formatted data systems provide users with tree-structured files or slightly more general network models of the data. In Section 1, inadequacies of these models are discussed. A model based on n-ary relations, a normal form for data base relations, and the concept of a universal data sublanguage are introduced. In Section 2, certain operations on relations (other than logical inference) are discussed and applied to the problems of redundancy and consistency in the user's model.
4,990 citations
Book•
01 Jan 1979
TL;DR: This book goes into the details of database conception and use, it tells you everything on relational databases from theory to the actual used algorithms.
Abstract: This book goes into the details of database conception and use, it tells you everything on relational databases. from theory to the actual used algorithms.
2,475 citations
Book•
01 Jan 1985
TL;DR: "Generalized Phrase Structure Grammar" provides the definitive exposition of the theory of grammar originally proposed by Gerald Gazdar and developed during half a dozen years' work with his colleagues Ewan Klein, Geoffrey Pullum, and Ivan Sag.
Abstract: "Generalized Phrase Structure Grammar" provides the definitive exposition of the theory of grammar originally proposed by Gerald Gazdar and developed during half a dozen years' work with his colleagues Ewan Klein, Geoffrey Pullum, and Ivan Sag. This long-awaited book contains both detailed specifications of the theory and extensive illustrations of its power to describe large parts of English grammar. Experts who wish to evaluate the theory and students learning GPSP for the first time will find this book an invaluable guide.The initial chapters lay out the theoretical machinery of GPSP in a readily intelligible way. Combining informal discussion with precise formalization, the authors describe all major aspects of their grammatical system, including a complete theory of syntactic features, phrase structure rules, meta rules, and feature instantiation principles. The book then shows just what a GPSP analysis of English syntax can accomplish. Topics include the internal structure of phrases, unbounded dependency constructions of many varieties, and coordinate conjunction a construction long considered the sticking point for phrase structure approaches to syntax.The book concludes with a well developed proposal for a model theoretic semantic system to go along with GPSP syntax. Throughout, the authors maintain the highest standards of explicitness and rigor in developing and assessing their grammatical system. Their aim is to provide the best possible test of the hypothesis that syntactic description can be accomplished in a single-level system. And more generally, it is their intention to formulate a grammatical framework in which linguistic universals follow directly from the form of the system and therefore require no explicit statement. Their book sets new methodological standards for work in generative grammar while presenting a grammatical system of extraordinary scope."
1,856 citations
"Natural language interfaces to data..." refers methods in this paper
...s are becoming increasingly influenced by principled linguistic theories, and they are often expressed in variations of well-known formalisms. Loqui [15], for example, uses a grammar influenced by Gpsg [43], and Cle’s [2] grammar is expressed in a unification-based formalism similar to Patr-II [84]. In many systems the syntax rules linking non-terminal symbols (non-leaf nodes in the parse tree) and the c...
[...]
Book•
01 Jan 1986
TL;DR: This book surveys the important concept of unification as it relates to linguistic theory and, in particular, to Functional Unification Grammar, Definite-Clause Grammars, Lexical- functions, and Generalized Phrase Struture Grammar.
Abstract: This book surveys the important concept of unification as it relates to linguistic theory and, in particular, to Functional Unification Grammar, Definite-Clause Grammars, Lexical-Function Grammar, Generalized Phrase Struture Grammar, and Head-Driven Phrase Structure Grammar. The notes include careful and correct definitions, as well as well-chosen examples of actual grammars, and a discussion of the relationships of computational systems and linguistic theories which use ideas from unification.
902 citations
Additional excerpts
...Loqui [15], for example, uses a grammar in uenced by Gpsg [43], and Cle's [2] grammar is expressed in a uni cation-based formalism similar to Patr-II [84]....
[...]
...Loqui [15], for example, uses a grammar influenced by Gpsg [43], and Cle’s [2] grammar is expressed in a unification-based formalism similar to Patr-II [84]....
[...]
Book•
01 Jan 1981
TL;DR: This book discusses Montague's Intensional Logic, a Higher-Order Type-Theoretic Language, and some Unresolved Issues with Possible Worlds Semantics and Propositional Attitudes.
Abstract: 1. Introduction.- 2. The Syntax and Semantics of Two Simple Languages.- I. The Language L0.- 1. Syntax of L0.- 2. Semantics of L0.- II. The Language L0E.- 1. Syntax of L0E.- 2. Semantics of L0E.- 3. Alternative Formulations of L0E and L0.- III. A Synopsis of Truth-Conditional Semantics.- IV. The Notion of Truth Relative to a Model.- V. Validity and Entailment Defined in Terms of Possible Models.- VI. Model Theory and Deductive Systems.- Exercises.- Note.- 3. First-Order Predicate Logic.- I. The Language L1.- 1. Syntax of L1.- 2. Semantics of L1.- II. The Language L1E.- 1. Syntax of L1E.- 2. Semantics of L1E.- Exercises.- Notes.- 4. A Higher-Order Type-Theoretic Language.- I. A Notational Variant of L1.- II. The Language Ltype.- 1. Syntax of Ltype.- 2. Semantics of Ltype.- III. Lambda Abstraction and the Language L?.- Exercises.- Notes.- 5. Tense and Modal Operators.- I. Tense Operators and Their Interpretation.- II. The Other Varieties of Modal Logic the Operators ? and ?.- III. Languages Containing Both Tense and Modal Operators: Coordinate Semantics.- Exercises.- Notes.- 6. Montague's Intensional Logic.- I. Compositionality and the Intension-Extension Distinction.- II. The Intensional Logic of PTQ.- 1. Syntax of IL.- 2. Semantics of IL.- III. Examples of 'Oblique Contexts' as Represented in IL.- IV. Some Unresolved Issues with Possible Worlds Semantics and Propositional Attitudes.- Notes.- 7. The Grammar of PTQ.- I. The Overall Organization of the PTQ Grammar.- 1. The Syntactic Categories of English in the PTQ Grammar.- 2. The Correspondence Between Categories of English and Types of IL.- II. Subject-Predicate and Determiner-Noun Rules.- III. Conjoined Sentences, Verb Phrases, and Term Phrases.- IV. Anaphoric Pronouns as Bound Variables Scope Ambiguities and Relative Clauses.- V. Be, Transitive Verbs, Meaning Postulates, and Non-Specific Readings.- VI. Adverbs and Infinitive Complement Verbs.- VII. De dicto Pronouns and Some Pronoun Problems.- VIII. Prepositions, Tenses, and Negation.- Exercises.- Notes.- 8. Montague's General Semiotic Program.- 9. An Annotated Bibliography of Further Work in Montague Semantics.- Appendix I: Index of Symbols.- Appendix II: Variable Type Conventions for Chapter 7.- Notes.- References.- Answers to Selected Problems and Exercises.
812 citations
"Natural language interfaces to data..." refers methods in this paper
...nsforms the parse tree to the intermediate logic query, using semantic rules similar to the mapping rules of section 5.2. Some systems (e.g. Janus [59]) build on the Montague-semantics tradition [71] [38], and carry out the semantic interpretation in a compositional, rule-to-rule manner. Each syntax rule is coupled to a semantics rule. The semantics rule computes the logic expression of the constituen...
[...]
...be a principled multi-stage transformation process, used in the Nlidb developed at the University of Essex. The Essex system first generates a logic query, expressed in a version of untyped λ-calculus [38]. The λ-calculus expression is then transformed into a first-order predicate logic expression, which is subsequently translated into universal-domain relational calculus, domain relational calculus, tu...
[...]