Book ChapterDOI
Inferring Attribute Grammars with Structured Data for Natural Language Processing
Bradford Craig Starkie
- pp 237-248
Reads0
Chats0
TLDR
The method presented in this paper has the ability to infer attribute grammars that can generate a wide range of useful data structures such as simple and structured types, lists, concatenated strings, and natural numbers.Abstract:
This paper presents a method for inferring reversible attribute grammars from tagged natural language sentences. Attribute grammars are a form of augmented context free grammar that assign "meaning" in the form of a data structure to a string in a context free language. The method presented in this paper has the ability to infer attribute grammars that can generate a wide range of useful data structures such as simple and structured types, lists, concatenated strings, and natural numbers. The method also presents two new forms of grammar generalisation; generalisation based upon identification of optional phrases and generalisation based upon lists. The method has been applied to and tested on the task of the rapid development of spoken dialog systems.read more
Citations
More filters
Patent
Generating natural language outputs
TL;DR: In this article, a set of triples are used to map voice queries and answers to sentence structures that may be used as an output answer to the voice query to generate natural language outputs.
Patent
System and process for developing a voice application
TL;DR: In this article, a dialog element selector for defining execution paths of the application by selecting dialog elements and adding the dialog elements to a tree structure, each path through the tree structure representing one of the execution paths.
Journal ArticleDOI
A survey of grammatical inference in software engineering
Andrew Stevenson,James R. Cordy +1 more
TL;DR: The theory of grammatical inference is introduced and the state of the art as it relates to software engineering is reviewed, as well as a variety of applications in software engineering, including programming languages, DSLs, visual languages, and execution traces.
Patent
A development system for a dialog system
TL;DR: In this paper, a scenario generator is used to generate a plurality of sample interactions representative of interactions between a dialog system and a user of the dialog system on the basis of definition data for the system.
Patent
System for predicting speec recognition accuracy and development for a dialog system
TL;DR: In this paper, a system for estimating the speech recognition accuracy achievable when using a dialog system and the number of example input phrases required to achieve a desired speech recognition performance is presented.
References
More filters
Book
Introduction to Modern Information Retrieval
Gerard Salton,Michael J. McGill +1 more
TL;DR: Reading is a need and a hobby at once and this condition is the on that will make you feel that you must read.
Journal ArticleDOI
Semantics of context-free languages
TL;DR: The implications of this process when some of the attributes of a string are “synthesized”, i.e., defined solely in terms of attributes of thedescendants of the corresponding nonterminal symbol, while other attributes are ‘inherited’, are examined.
Book
Statistical Language Learning
TL;DR: In this article, Charniak presents statistical language processing from an artificial intelligence point of view in a text for researchers and scientists with a traditional computer science background, which is grounded in real text and therefore promises to produce usable results.
Posted Content
Inducing Probabilistic Grammars by Bayesian Model Merging
TL;DR: In this paper, the authors describe a framework for inducing probabilistic grammars from corpora of positive samples, where samples are incorporated by adding ad-hoc rules to a working grammar; subsequently, elements of the model (such as states or nonterminals) are merged to achieve generalization and a more compact representation.
Bayesian learning of probabilistic language models
TL;DR: A version of Earley's parser is presented that solves the standard problems associated with SCFGs efficiently, including the computation of sentence probabilities and sentence prefix probabilities, finding most likely parses, and the estimation of grammar parameters.