Results 1 to 10 of about 521,807 (336)
Online Learning for Statistical Machine Translation [PDF]
Computational Linguistics, 2021 We present online learning techniques for statistical machine translation (SMT). The availability of large training data sets that grow constantly over time is becoming more and more frequent in the field of SMT—for example, in the context of translation
Daniel Ortiz-Martínez
doaj +4 more sources
Optimization for Statistical Machine Translation: A Survey [PDF]
Computational Linguistics, 2023 In statistical machine translation (SMT), the optimization of the system parameters to maximize translation accuracy is now a fundamental part of virtually all modern systems.
Graham Neubig, Taro Watanabe
doaj +3 more sources
Unsupervised Statistical Machine Translation [PDF]
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018 While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018).
Mikel Artetxe +2 more
semanticscholar +6 more sources
Pushdown Automata in Statistical Machine Translation [PDF]
Computational Linguistics, 2023 This article describes the use of pushdown automata (PDA) in the context of statistical machine translation and alignment under a synchronous context-free grammar. We use PDAs to compactly represent the space of candidate translations generated by the grammar when applied to an input sentence. General-purpose PDA algorithms for replacement, composition,
Cyril Allauzen +4 more
doaj +3 more sources
Evaluation of English–Slovak Neural and Statistical Machine Translation
Applied Sciences, 2021 This study is focused on the comparison of phrase-based statistical machine translation (SMT) systems and neural machine translation (NMT) systems using automatic metrics for translation quality evaluation for the language pair of English and Slovak.
Lucia Benkova +3 more
doaj +2 more sources
Optimizing Statistical Machine Translation for Text Simplification
Transactions of the Association for Computational Linguistics, 2021 Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus.
Wei Xu +4 more
doaj +2 more sources
Decoding algorithm in statistical machine translation [PDF]
Proceedings of the eighth conference on European chapter of the Association for Computational Linguistics -, 1997 Decoding algorithm is a crucial part in statistical machine translation. We describe a stack decoding algorithm in this paper. We present the hypothesis scoring method and the heuristics used in our algorithm. We report several techniques deployed to improve the performance of the decoder.
Ye‐Yi Wang, Alex Waibel
openalex +7 more sources
Statistical Machine Translation
Computational Linguistics, 2013 Statistical Machine Translation (SMT) is an approach to automatic text translation based on the use of statistical models and examples of translations. SMT is the current dominant research paradigm for machine translation and has been attracting significant commercial interest in recent years. In this chapter, the authors introduce the rationale behind
Lucia Specia
doaj +2 more sources
String-to-Dependency Statistical Machine Translation [PDF]
Computational Linguistics, 2021 We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model.
Libin Shen, Jinxi Xu, Ralph Weischedel
doaj +3 more sources
MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation
Journal of Intelligent Systems, 2019 Machine translation (MT) is the automatic translation of the source language to its target language by a computer system. In the current paper, we propose an approach of using recurrent neural networks (RNNs) over traditional statistical MT (SMT).
Mahata Sainik Kumar +2 more
doaj +2 more sources