Results 1  10
of
379
Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora
, 1997
"... ..."
FiniteState Transducers in Language and Speech Processing
 Computational Linguistics
, 1997
"... Finitestate machines have been used in various domains of natural language processing. We consider here the use of a type of transducers that supports very efficient programs: sequential transducers. We recall classical theorems and give new ones characterizing sequential stringtostring transducer ..."
Abstract

Cited by 382 (42 self)
 Add to MetaCart
Finitestate machines have been used in various domains of natural language processing. We consider here the use of a type of transducers that supports very efficient programs: sequential transducers. We recall classical theorems and give new ones characterizing sequential stringtostring transducers. Transducers that output weights also play an important role in language and speech processing. We give a specific study of stringtoweight transducers, including algorithms for determinizing and minimizing these transducers very efficiently, and characterizations of the transducers admitting determinization and the corresponding algorithms. Some applications of these algorithms in speech recognition are described and illustrated. 1.
Weighted finitestate transducers in speech recognition
 COMPUTER SPEECH & LANGUAGE
, 2002
"... We survey the use of weighted finitestate transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for hidden Markov models (HMMs), contextdependency, pronunciation dictionaries, grammars, and alternative recognition outputs. Furthermore, general tr ..."
Abstract

Cited by 203 (5 self)
 Add to MetaCart
(Show Context)
We survey the use of weighted finitestate transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for hidden Markov models (HMMs), contextdependency, pronunciation dictionaries, grammars, and alternative recognition outputs. Furthermore, general transducer operations combine these representations flexibly and efficiently. Weighted determinization and minimization algorithms optimize their time and space requirements, and a weight pushing algorithm distributes the weights along the paths of a weighted transducer optimally for speech recognition. As an example, we describe a North American Business News (NAB) recognition system built using these techniques that combines the HMMs, full crossword triphones, a lexicon of 40 000 words, and a large trigram grammar into a single weighted transducer that is only somewhat larger than the trigram word grammar and that runs NAB in realtime on a very simple decoder. In another example, we show that the same techniques can be used to optimize lattices for secondpass recognition. In a third example, we show how general automata operations can be used to assemble lattices from different recognizers to improve recognition performance.
Speech Recognition by Composition of Weighted Finite Automata
 FINITESTATE LANGUAGE PROCESSING
, 1996
"... We present a general framework based on weighted finite automata and weighted finitestate transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data structures used in recognition, including contextdependent u ..."
Abstract

Cited by 135 (11 self)
 Add to MetaCart
We present a general framework based on weighted finite automata and weighted finitestate transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data structures used in recognition, including contextdependent units, pronunciation dictionaries, language models and lattices. Furthermore, general but efficient algorithms can used for combining information sources in actual recognizers and for optimizing their application. In particular, a single composition algorithm is used both to combine in advance information sources such as language models and dictionaries, and to combine acoustic observations and information sources dynamically during recognition.
PartofSpeech Tagging and Partial Parsing
 CorpusBased Methods in Language and Speech
, 1996
"... m we can carve o# next. `Partial parsing' is a cover term for a range of di#erent techniques for recovering some but not all of the information contained in a traditional syntactic analysis. Partial parsing techniques, like tagging techniques, aim for reliability and robustness in the face of t ..."
Abstract

Cited by 111 (0 self)
 Add to MetaCart
(Show Context)
m we can carve o# next. `Partial parsing' is a cover term for a range of di#erent techniques for recovering some but not all of the information contained in a traditional syntactic analysis. Partial parsing techniques, like tagging techniques, aim for reliability and robustness in the face of the vagaries of natural text, by sacrificing completeness of analysis and accepting a low but nonzero error rate. 1 Tagging The earliest taggers [35, 51] had large sets of handconstructed rules for assigning tags on the basis of words' character patterns and on the basis of the tags assigned to preceding or following words, but they had only small lexica, primarily for exceptions to the rules. TAGGIT [35] was used to generate an initial tagging of the Brown corpus, which was then handedited. (Thus it provided the data that has since been used to train other taggers [20].) The tagger described by Garside [56, 34], CLAWS, was a probabilistic version of TAGGIT, and the DeRose tagger improved on
The Design Principles of a Weighted FiniteState Transducer Library
, 2002
"... We describe the algorithmic and software design principles of an objectoriented library for weighted finitestate transducers. By taking advantage of the theory of rational power series, we were able to achieve high degrees of generality, modularity and irredundancy, while attaining competitive eff ..."
Abstract

Cited by 108 (20 self)
 Add to MetaCart
We describe the algorithmic and software design principles of an objectoriented library for weighted finitestate transducers. By taking advantage of the theory of rational power series, we were able to achieve high degrees of generality, modularity and irredundancy, while attaining competitive efficiency in demanding speech processing applications involving weighted automata of more than 10 7 states and transitions. Besides its mathematical foundation, the design also draws from important ideas in algorithm design and programming languages: dynamic programming and shortestpaths algorithms over general semirings, objectoriented programming, lazy evaluation and memoization.
Deterministic PartofSpeech Tagging with FiniteState Transducers
 Computational Linguistics
, 1995
"... Stochastic approaches to natural language processing have often been preferred to rulebased approaches because of their robustness and their automatic training capabilities. This was the case for partofspeech tagging until Brill showed how stateoftheart partofspeech tagging can be achieved w ..."
Abstract

Cited by 94 (0 self)
 Add to MetaCart
Stochastic approaches to natural language processing have often been preferred to rulebased approaches because of their robustness and their automatic training capabilities. This was the case for partofspeech tagging until Brill showed how stateoftheart partofspeech tagging can be achieved with a rulebased tagger by inferring rules from a training corpus. However, current implementations of the rulebased tagger run more slowly than previous approaches. In this paper, we present a finitestate tagger, inspired by the rulebased tagger, that operates in optimal time in the sense that the time to assign tags to a sentence corresponds to the time required to follow a single path in a deterministic finitestate machine. This result is achieved by encoding the application of the rules found in the tagger as a nondeterministic finitestate transducer and then turning it into a deterministic transducer. The resulting deterministic transducer yields a partofspeech tagger whose speed is dominated by the access time of mass storage devices. We then generalize the techniques to the class of transformationbased systems. 1.
FiniteState Transducers
 in Speech Recognition. Computer Speech and Language
, 1997
"... Abstract. psubsequential transducers are efficient finitestate transducers with p final outputs used in a variety of applications. Not all transducers admit equivalent psubsequential transducers however. We briefly describe an existing generalized determinization algorithm for psubsequential tran ..."
Abstract

Cited by 92 (20 self)
 Add to MetaCart
(Show Context)
Abstract. psubsequential transducers are efficient finitestate transducers with p final outputs used in a variety of applications. Not all transducers admit equivalent psubsequential transducers however. We briefly describe an existing generalized determinization algorithm for psubsequential transducers and give the first characterization of psubsequentiable transducers, transducers that admit equivalent psubsequential transducers. Our characterization shows the existence of an efficient algorithm for testing psubsequentiability. We have fully implemented the generalized determinization algorithm and the algorithm for testing psubsequentiability. We report experimental results showing that these algorithms are practical in largevocabulary speech recognition applications. The theoretical formulation of our results is the equivalence of the following three properties for finitestate transducers: determinizability in the sense of the generalized algorithm, psubsequentiability, and the twins property. 1
Weighted Automata in Text and Speech Processing
 IN ECAI96 WORKSHOP
, 1996
"... Finitestate automata are a very effective tool in natural language processing. However, in a variety of applications and especially in speech precessing, it is necessary to consider more general machines in which arcs are assigned weights or costs. We briefly describe some of the main theoretical a ..."
Abstract

Cited by 88 (37 self)
 Add to MetaCart
Finitestate automata are a very effective tool in natural language processing. However, in a variety of applications and especially in speech precessing, it is necessary to consider more general machines in which arcs are assigned weights or costs. We briefly describe some of the main theoretical and algorithmic aspects of these machines. In particular, we describe an efficient composition algorithm for weighted transducers, and give examples illustrating the value of determinization and minimization algorithms for weighted automata.
Optimality theory and the generative complexity of constraint violability
 COMPUTATIONAL LINGUISTICS
, 1998
"... It has been argued that rulebased phonological descriptions can uniformly be expressed as mappings carried out by finitestate transducers, and therefore fall within the class of rational relations. If this property of generative capacity is an empirically correct characterization of phonological ..."
Abstract

Cited by 87 (2 self)
 Add to MetaCart
It has been argued that rulebased phonological descriptions can uniformly be expressed as mappings carried out by finitestate transducers, and therefore fall within the class of rational relations. If this property of generative capacity is an empirically correct characterization of phonological mappings, it should hold of any sufficiently restrictive theory of phonology, whether it utilizes constraints or rewrite rules. In this paper, we investigate the conditions under which the phonological descriptions that are possible within the view of constraint interaction embodied in Optimality Theory (Prince and Smolensky 1993) remain within the class of rational relations. We show that this is true when GEN is itself a rational relation, and each of the constraints distinguishes among finitely many regular sets of candidates.