A tree-trellis n-best decoder for stochastic context-free grammars
نویسنده
چکیده
In this paper a decoder for continuous speech recognition using stochastic context-free grammars is described. It forms the backbone of the ACE recognizer, which is a modular system for real-time speech recognition. A new rationale for automata is introduced, as well as a new model for pruning the search space.
منابع مشابه
An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems in stochastic naturallanguage processing. Comparing the performance of PLTIGs with non-hierarchicalN -gram models and PCFGs, we show that PLTIG combines the best aspects of both, with language modeli...
متن کاملStochastic Categorial Grammars
Statistical methods have turned out to be quite successful in natural language processing. During the recent years, several models of stochastic grammars have been proposed, including models based on lexicalised context-free grammars [3], tree adjoining grammars [15], or dependency grammars [2, 5]. In this exploratory paper, we propose a new model of stochastic grammar, whose originality derive...
متن کاملStochastic Tree-Adjoining Grammars
A B S T R A C T The notion of stochastic lexicalized tree-adjoining grammar (SLTAG) is defined and basic algorithms for SLTAG are designed. The parameters of a SLTAG correspond to the probability of combining two structures each one associated with a word. The characteristics of SLTAG are unique and novel since it is lexically sensitive (as N-gram models or Hidden Markov Models) and yet hierarc...
متن کاملFormal grammars Lectures ??–??. Linear grammars and trellis automata
The linear case of context-free, conjunctive and Boolean grammars. Trellis automata. Examples. Equivalence of grammars and automata. 1 Linear Boolean grammars Definition 1. A Boolean grammar G = (Σ, N, P, S) is said to be linear if every rule A→ α1& . . .&αm&¬β1& . . .&¬βn, has αi, βj ∈ Σ∗ ∪ (Σ ∪N)∗. If a linear Boolean grammar is conjunctive (context-free), it is called a linear conjunctive (l...
متن کاملA Trellis-Based Algorithm For Estimating The Parameters Of Hidden Stochastic Context-Free Grammar
I N T R O D U C T I O N The algorithm described in this paper is concerned with using hidden Markov methods for estimation of the parameters of a stochastic context-free grammar from free text. The Forward/Backward (F/B) algorithm (Baum, 1972) is capable of estimating the parameters of a hidden Markov model (i.e. a hidden stochastic regular grammar) and has been used with success to train text ...
متن کامل