Neural Networks Classifier for Data Selection in Statistical Machine Translation

Abstract Corpora are precious resources, as they allow for a proper estimation of statistical machine translation models. Data selection is a variant of the domain adaptation field, aimed to extract those sentences from an out-of-domain corpus that are the most useful to translate a different target domain. We address the data selection problem in statistical machine translation as a classification task. We present a new method, based on neural networks, able to deal with monolingual and bilingual corpora. Empirical results show that our data selection method provides slightly better translation quality, compared to a state-of-the-art method (cross-entropy), requiring substantially less data. Moreover, the results obtained are coherent across different language pairs, demonstrating the robustness of our proposal.

• Publication year

  2016

• Venue

  Prague Bulletin of Mathematical Linguistics

• Publication date

  2016-12-16

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1515/pralin-2017-0027arXiv 1612.05555
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Domain adaptation using neural network joint model

  2017cited by this paper
• Semi-supervised Convolutional Networks for Translation Adaptation with Tiny Amount of In-domain Data

  2016cited by this paper
• Theano: A Python framework for fast computation of mathematical expressions

  2016cited by this paper
• Bilingual Methods for Adaptive Training Data Selection for Machine Translation

  2016cited by this paper
• Semi-supervised Learning with Ladder Networks

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Going deeper with convolutions

  2014cited by this paper
• Statistical Machine Translation

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Convolutional Neural Networks for Sentence Classification

  2014influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Latent Domain Translation Models in Mix-of-Domains Haystack

  2014cited by this paper
• Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation

  2013cited by this paper
• XenC: An Open-Source Tool for Data Selection in Natural Language Processing

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Recurrent Continuous Translation Models

  2013cited by this paper
• Large, Pruned or Continuous Space Language Models on a GPU for Statistical Machine Translation

  2012cited by this paper
• ADADELTA: An Adaptive Learning Rate Method

  2012cited by this paper
• Combining translation and language model scoring for domain-specific data filtering

  2011cited by this paper
• Domain Adaptation via Pseudo In-Domain Data Selection

  2011cited by this paper
• Intelligent Selection of Language Model Training Data

  2010cited by this paper
• News from OPUS — A collection of multilingual parallel corpora with tools and interfaces

  2009cited by this paper
• Large Language Models in Machine Translation

  2007cited by this paper
• (Meta-) Evaluation of Machine Translation

  2007cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• Open Source Toolkit for Statistical Machine Translation: Factored Translation Models and Lattice Decoding

  2006cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005cited by this paper
• Minimum Error Rate Training in Statistical Machine Translation

  2003cited by this paper
• A Systematic Comparison of Various Statistical Alignment Models

  2003cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002influential reference
• SRILM - an extensible language modeling toolkit

  2002cited by this paper
• Learning to Forget: Continual Prediction with LSTM

  2000cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Improved backing-off for M-gram language modeling

  1995cited by this paper
• Unsupervised Word Sense Disambiguation Rivaling Supervised Methods

  1995cited by this paper

• Machine Translation in the Era of Large Language Models:A Survey of Historical and Emerging Problems

  2025cites this paper
• Parallel feature weight decay algorithms for fast development of machine translation models

  2021cites this paper
• Semantic-Aware Deep Neural Attention Network for Machine Translation Detection

  2021cites this paper
• UDON: Unsupervised Data SelectiON for Biomedical Entity Recognition

  2021cites this paper
• Accelerating Text Communication via Abbreviated Sentence Input

  2021cites this paper
• The UET-ICTU Submissions to the VLSP 2020 News Translation Task

  2020cites this paper
• Unsupervised Domain Clusters in Pretrained Language Models

  2020cites this paper
• Data selection for NMT using Infrequent n-gram Recovery

  2018cites this paper
• NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning

  2018influential citation
• Using Tectogrammatical Annotation for Studying Actors and Actions in Sallust’s Bellum Catilinae

  2018cites this paper
• Creating the best development corpus for Statistical Machine Translation systems

  2018cites this paper
• Creating a strong statistical machine translation system by combining different decoders

  2018cites this paper
• Speech corpora subset selection based on time-continuous utterances features

  2018cites this paper
• the 21st Annual Conference of the European Association for Machine Translation

  2018cites this paper
• The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2017

  2017cites this paper
• Exploiting Relative Frequencies for Data Selection

  2017cites this paper
• Domain adaptation for statistical machine translation and neural machine translation

  2017cites this paper