Margin Infused Relaxed Algorithm for Moses
TL;DR: An open-source implementation of the Margin Infused Relaxed Algorithm for statistical machine translation (SMT) is described and experimental results comparing the performance of MIRA with MERT in terms of translation quality and stability are reported.
read more
Abstract: We describe an open-source implementation of the Margin Infused Relaxed Algorithm (MIRA) for statistical machine translation (SMT). The implementation is part of the Moses toolkit and can be used as an alternative to standard minimum error rate training (MERT). A description of the implementation and its usage on core feature sets as well as large, sparse feature sets is given and we report experimental results comparing the performance of MIRA with MERT in terms of translation quality and stability.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Parallel Optimization: Theory, Algorithms and Applications
TL;DR: Yair Censor and Stavros A. Zenios, Oxford University Press, New York, 1997, 539 pp.
579
Fill-up versus Interpolation Methods for Phrase-based SMT Adaptation
Arianna Bisazza,Nicholas Ruiz,Marcello Federico +2 more
- 09 Dec 2011
TL;DR: This paper compares techniques to combine diverse parallel corpora for domain-specific phrase-based SMT system training and focuses on phrase table fill-up: a method that effectively exploits background knowledge to improve model coverage, while preserving the more reliable information coming from the in-domain corpus.
Multimodal Pivots for Image Caption Translation
TL;DR: This work presents an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space, and relies on available large datasets of monolingually captioned images, and on state-of-the-art convolutional neural networks to compute image similarities.
91
Multimodal Pivots for Image Caption Translation
Julian Hitschler,Shigehiko Schamoni,Stefan Riezler +2 more
- 01 Jan 2016
TL;DR: This article proposed an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space, which performs image retrieval over a database of images that are captioned in the target language, and use the captions of the most similar images for cross-lingual re-ranking of translation outputs.
89
Patent
Estimation of parameters for machine translation without in-domain parallel data
Prashant Mathur,Sriram Venkatapathy,Nicola Cancedda +2 more
- 14 Apr 2014
TL;DR: In this article, a system and method for estimating parameters for features of a translation scoring function for scoring candidate translations in a target domain is provided, where a similarity measure is computed between the source corpus and a target-domain multi-model, which may be a phrase table derived from phrase tables of comparative domains, weighted as a function of similarity with the target corpus.
64
References
Support-Vector Networks
Corinna Cortes,Vladimir Vapnik +1 more
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Bleu: a Method for Automatic Evaluation of Machine Translation
Kishore Papineni,Salim Roukos,Todd Ward,Wei-Jing Zhu +3 more
- 06 Jul 2002
TL;DR: This paper proposed a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run.
•Journal Article
Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines
TL;DR: The sequential minimal optimization (SMO) algorithm as mentioned in this paper uses a series of smallest possible QP problems to solve a large QP problem, which avoids using a time-consuming numerical QP optimization as an inner loop.
•Journal Article
Online Passive-Aggressive Algorithms
TL;DR: This work presents a unified view for online classification, regression, and uni-class problems, and proves worst case loss bounds for various algorithms for both the realizable case and the non-realizable case.
•Book
Statistical Machine Translation
Philipp Koehn
- 18 Jan 2010
TL;DR: This introductory text to statistical machine translation (SMT) provides all of the theories and methods needed to build a statistical machine translator, such as Google Language Tools and Babelfish, and the companion website provides open-source corpora and tool-kits.