Results 1 
9 of
9
Novel reordering approaches in phrasebased statistical machine translation
 Proceedings of the ACL Workshop on Building and Using Parallel Texts: DataDriven Machine Translation and Beyond
, 2005
"... This paper presents novel approaches to reordering in phrasebased statistical machine translation. We perform consistent reordering of source sentences in training and estimate a statistical translation model. Using this model, we follow a phrasebased monotonic machine translation approach, for wh ..."
Abstract

Cited by 33 (14 self)
 Add to MetaCart
This paper presents novel approaches to reordering in phrasebased statistical machine translation. We perform consistent reordering of source sentences in training and estimate a statistical translation model. Using this model, we follow a phrasebased monotonic machine translation approach, for which we develop an efficient and flexible reordering framework that allows to easily introduce different reordering constraints. In translation, we apply source sentence reordering on word level and use a reordering automaton as input. We show how to compute reordering automata ondemand using IBM or ITG constraints, and also introduce two new types of reordering constraints. We further add weights to the reordering automata. We present detailed experimental results and show that reordering significantly improves translation quality. 1
A novel stringtostring distance measure with applications to machine translation evaluation
 MT Summit IX
, 2003
"... We introduce a stringtostring distance measure which extends the edit distance by block transpositions as constant cost edit operation. An algorithm for the calculation of this distance measure in polynomial time is presented. We then demonstrate how this distance measure can be used as an evaluat ..."
Abstract

Cited by 33 (4 self)
 Add to MetaCart
We introduce a stringtostring distance measure which extends the edit distance by block transpositions as constant cost edit operation. An algorithm for the calculation of this distance measure in polynomial time is presented. We then demonstrate how this distance measure can be used as an evaluation criterion in machine translation. The correlation between this evaluation criterion and human judgment is systematically compared with that of other automatic evaluation measures on two translation tasks. In general, like other automatic evaluation measures, the criterion shows low correlation at sentence level, but good correlation at system level. 1
Probabilistic FiniteState Machines  Part I
"... Probabilistic finitestate machines are used today in a variety of areas in pattern recognition, or in fields to which pattern recognition is linked: computational linguistics, machine learning, time series analysis, circuit testing, computational biology, speech recognition and machine translatio ..."
Abstract

Cited by 15 (1 self)
 Add to MetaCart
Probabilistic finitestate machines are used today in a variety of areas in pattern recognition, or in fields to which pattern recognition is linked: computational linguistics, machine learning, time series analysis, circuit testing, computational biology, speech recognition and machine translation are some of them. In part I of this paper we survey these generative objects and study their definitions and properties. In part II, we will study the relation of probabilistic finitestate automata with other well known devices that generate strings as hidden Markov models and ngrams, and provide theorems, algorithms and properties that represent a current state of the art of these objects.
FiniteState Transducers For SpeechInput Translation
 IEEE Automatic Speech Recognition and Understanding Workhsop, ASRU’01
, 2001
"... Nowadays, hidden Markov models (HMMs) and ngrams are the basic components of the most successful speech recognition systems. In such systems, HMMs (the acoustic models) are integrated into a ngram or a stochastic finitestate grammar (the language model). Similar models can be used for speech tra ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
Nowadays, hidden Markov models (HMMs) and ngrams are the basic components of the most successful speech recognition systems. In such systems, HMMs (the acoustic models) are integrated into a ngram or a stochastic finitestate grammar (the language model). Similar models can be used for speech translation, and HMMs (the acoustic models) can be integrated into a finitestate transducer (the translation model). Moreover, the translation process can be performed by searching for an optimal path of states in the integrated network. The output of this search process is a target word sequence associated to the optimal path. In speech translation, HMMs can be trained from a source speech corpus, and the translation model can be learned automatically from a parallel training corpus.
AER: Do we need to “improve” our alignments
 In Proceedings of the International Workshop on Spoken Language Translation
, 2006
"... Currently most statistical machine translation systems make use of alignments as a first step in the process of training the actual translation models. Several researchers have investigated how to improve the alignment quality, with the (intuitive) assumption that better alignments increase the tran ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
Currently most statistical machine translation systems make use of alignments as a first step in the process of training the actual translation models. Several researchers have investigated how to improve the alignment quality, with the (intuitive) assumption that better alignments increase the translation quality. In this paper we will investigate this assumption and show that this is not always the case. 1.
Large Scale Inference of Deterministic Transductions: Tenjinno Problem 1
"... Abstract. We discuss the problem of large scale grammatical inference in the context of the Tenjinno competition, with reference to the inference of deterministic finite state transducers, and discuss the design of the algorithms and the design and implementation of the program that solved the first ..."
Abstract
 Add to MetaCart
Abstract. We discuss the problem of large scale grammatical inference in the context of the Tenjinno competition, with reference to the inference of deterministic finite state transducers, and discuss the design of the algorithms and the design and implementation of the program that solved the first problem. Though the OSTIA algorithm has good asymptotic guarantees for this class of problems, the amount of data required is prohibitive. We therefore developed a new strategy for inferring large scale transducers that is more adapted for large random instances of the type in question, which involved combining traditional state merging algorithms for inference of finite state automata with EM based alignment algorithms and state splitting algorithms. 1
SpeechToSpeech Translation Based On FiniteState Transducers
 In Proc. Int. Conf. on Acoustics, Speech, and Signal Processing
, 2001
"... Nowadays, the most successful speech recognition systems are based on stochastic finitestate networks (hidden Markov models and ngrams). Speech translation can be accomplished in a similar way as speech recognition. Stochastic finitestate transducers, which are specific stochastic finitestate net ..."
Abstract
 Add to MetaCart
Nowadays, the most successful speech recognition systems are based on stochastic finitestate networks (hidden Markov models and ngrams). Speech translation can be accomplished in a similar way as speech recognition. Stochastic finitestate transducers, which are specific stochastic finitestate networks, have proved very adequate for translation modeling. In this work a speechtospeech translation system, the EUTRANS system, is presented. The acoustic, language and translation models are finitestate networks that are automatically learnt from training samples. This system was assessed in a series of translation experiments from Spanish to English and from Italian to English in an application involving the interaction (by telephone) of a customer with a receptionist at the frontdesk of a hotel.
A Novel StringtoString Distance Measure With Applications to
 In Proceedings of MT Summit IX
, 2003
"... We introduce a stringtostring distance measure which extends the edit distance by block transpositions as constant cost edit operation. An algorithm for the calculation of this distance measure in polynomial time is presented. We then demonstrate how this distance measure can be used as an evalu ..."
Abstract
 Add to MetaCart
We introduce a stringtostring distance measure which extends the edit distance by block transpositions as constant cost edit operation. An algorithm for the calculation of this distance measure in polynomial time is presented. We then demonstrate how this distance measure can be used as an evaluation criterion in machine translation. The correlation between this evaluation criterion and human judgment is systematically compared with that of other automatic evaluation measures on two translation tasks. In general, like other automatic evaluation measures, the criterion shows low correlation at sentence level, but good correlation at system level.
Actively Learning Probabilistic Subsequential Transducers
 THE 11TH ICGI
, 2012
"... In this paper we investigate learning of probabilistic subsequential transducers in an active learning environment. In our learning algorithm the learner interacts with an oracle by asking probabilistic queries on the observed data. We prove our algorithm in an identification in the limit model. We ..."
Abstract
 Add to MetaCart
In this paper we investigate learning of probabilistic subsequential transducers in an active learning environment. In our learning algorithm the learner interacts with an oracle by asking probabilistic queries on the observed data. We prove our algorithm in an identification in the limit model. We also provide experimental evidence to show the correctness and to analyze the learnability of the proposed algorithm.