Sprachtheoretische Grundlagen F Ur Die Computer Linguistik Probabilistic Constraint Logic Programming
نویسنده
چکیده
This paper addresses two central problems for probabilistic processing models: parameter estimation from incomplete data and eecient retrieval of most probable analyses. These questions have been answered satisfactorily only for probabilistic regular and context-free models. We address these problems for a more expressive probabilistic constraint logic programming model. We present a log-linear probability model for probabilistic constraint logic programming. On top of this model we deene an algorithm to estimate the parameters and to select the properties of log-linear models from incomplete data. This algorithm is an extension of the improved iterative scaling algorithm of Della Pietra, Della Pietra, and Laaerty (1995). Our algorithm applies to log-linear models in general and is accompanied with suitable approximation methods when applied to large data spaces. Furthermore, we present an approach for searching for most probable analyses of the probabilistic constraint logic programming model. This method can be applied to the ambiguity resolution problem in natural language processing applications. 1. Introduction Rabiner (1989) identiied three basic problems of interest that must be solved for a Hidden Markov Model to be useful in real-world speech recognition applications: the parameter estimation problem, the optimal state sequence problem and the observation sequence probability problem. These problems generalize to arbitrary probabilistic symbol processing models in various real-world applications in an obvious manner. The rst two problems can be stated in a more general way as follows.
منابع مشابه
Sprachtheoretische Grundlagen F Ur Die Computer Linguistik Frank Morawietz : Monadic Second Order Logic, Tree Automata and Constraint Logic Programming Monadic Second Order Logic, Tree Automata and Constraint Logic Programming
In this paper we present a rst step toward the development of a constraint logic programming (clp) language R(MSO) based on monadic second order (mso) logic. We apply the scheme proposed by HH ohfeld and Smolka (1988) to obtain a relational extension of mso logic with a corresponding sound and complete operational semantics. The solutions to constraints expressed in monadic second order logic a...
متن کاملTagungsbesuch in Russland
Ende September 1992 machte die Arbeitsgruppe Quantitative Linguistik des Fachs Linguistische Datenverarbeitung/Computerlinguistik der Universität Trier zu einem Tagungsbesuch in Rußland auf den Weg. Zweck der Reise war der Besuch der Konferenz über linguistische Synergetik (COLISYN), die vom 22.9.1992 bis zum 25.9.1992 in den Räumen der Moskauer Universität stattfand. Die Konferenz war, gemesse...
متن کاملStatistical Inference and Probabilistic Modelling for Constraint-Based NLP
In this paper we present a probabilistic model for constraint-based grammars and a method for estimating the parameters of such models from incomplete, i.e., unparsed data. Whereas methods exist to estimate the parameters of probabilistic context-free grammars from incomplete data ([2]), so far for probabilistic grammars involving context-dependencies only parameter estimation techniques from c...
متن کاملInstitut F Ur Informatik Lehr-und Forschungseinheit F Ur Programmier-und Modellierungssprachen Oettingenstraae 67, D{80538 M Unchen Nurse Scheduling Using Constraint Logic Programming Nurse Scheduling Using Constraint Logic Programming
The nurse scheduling problem consists of assigning working shifts to each nurse on each day of a certain period of time. A typical problem comprises 600 to 800 assignments that have to take into account several requirements such as minimal allocation of a station , legal regulations and wishes of the personnel. This planning is a diicult and time-consuming expert task and is still done manually...
متن کامل