Domain Adaptation for Statistical Machine Translation

Statistical machine translation (SMT) systems perform poorly when it is applied to new target domains. Our goal is to explore domain adaptation approaches and techniques for improving the translation quality of domain-specific SMT systems. However, translating texts from a specific domain (e.g., medicine) is full of challenges. The first challenge is ambiguity. Words or phrases contain different meanings in different contexts. The second one is language style due to the fact that texts from different genres are always presented in different syntax, length and structural organization. The third one is the out-of-vocabulary words (OOVs) problem. In-domain training data are often scarce with low terminology coverage. In this thesis, we explore the state-of-the-art domain adaptation approaches and propose effective solutions to address those problems.

• Publication year

  2018

• Venue

  arXiv.org

• Publication date

  2018-04-05

• Fields of study

  Linguistics, Computer Science

• Identifiers
  arXiv 1804.01760
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Translating Pro-Drop Languages with Reconstruction Models

  2018cited by this paper
• Chinese-Portuguese Machine Translation: A Study on Building Parallel Corpora from Comparable Texts

  2018cited by this paper
• Conference Papers

  2018cited by this paper
• Exploiting Cross-Sentence Context for Neural Machine Translation

  2017cited by this paper
• A novel and robust approach for pro-drop language translation

  2017influential reference
• Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking

  2017cited by this paper
• A Novel Approach to Dropped Pronoun Translation

  2016cited by this paper
• Automatic Construction of Discourse Corpora for Dialogue Translation

  2016cited by this paper
• Dropped pronoun generation for dialogue machine translation

  2016influential reference
• PRAGUE, CZECH REPUBLIC

  2016cited by this paper
• The DCU Discourse Parser for Connective, Argument Identification and Explicit Sense Classification

  2015influential reference
• An Empirical Study of Smoothing Techniques for Language Modeling

  2015cited by this paper
• The DCU Discourse Parser: A Sense Classification Task

  2015influential reference
• Linguistically-augmented perplexity-based data selection for language models

  2015cited by this paper
• Effective Hypotheses Re-ranking Model in Statistical Machine Translation

  2014influential reference
• UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation

  2014cited by this paper
• Domain Adaptation for Medical Text Translation using Web Resources

  2014influential reference
• Statistical Machine Translation

  2014cited by this paper
• Combining Domain Adaptation Approaches for Medical Text Translation

  2014influential reference
• Factored Statistical Machine Translation for Grammatical Error Correction

  2014influential reference
• Adaptation of machine translation for multilingual information retrieval in the medical domain

  2014cited by this paper
• A Systematic Comparison of Data Selection Criteria for SMT Domain Adaptation

  2014influential reference
• Cross-Language Information Retrieval

  2014influential reference
• Data Selection via Semi-supervised Recursive Autoencoders for SMT Domain Adaptation

  2014cited by this paper
• An Experimental Platform for Cross-Language Document Retrieval

  2013influential reference
• Vector Space Model for Adaptation in Statistical Machine Translation

  2013cited by this paper
• Domain adaptation for translation models in statistical machine translation

  2013cited by this paper
• Synthesis Lectures on Human Language Technologies

  2013cited by this paper
• The CNGL-DCU-Prompsit Translation Systems for WMT13

  2013cited by this paper
• Free/Open-Source Rule-Based Machine Translation

  2013cited by this paper
• UM-Checker: A Hybrid System for English Grammatical Error Correction

  2013cited by this paper
• iCPE: A Hybrid Data Selection Model for SMT Domain Adaptation

  2013influential reference
• Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation

  2013cited by this paper
• Hybrid Selection of Language Model Training Data Using Linguistic Information and Perplexity

  2013cited by this paper
• Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data

  2013cited by this paper
• A New State-of-The-Art Czech Named Entity Recognizer

  2013cited by this paper
• The Joy of Parallelism with CzEng 1.0

  2012cited by this paper
• Domain Adaptation of Statistical Machine Translation using Web-Crawled Resources: A Case Study

  2012cited by this paper
• An Improvement in Cross-Language Document Retrieval Based on Statistical Models

  2012cited by this paper
• CRFs-Based Chinese Word Segmentation for Micro-Blog with Small-Scale Data

  2012influential reference
• Parallel Data, Tools and Interfaces in OPUS

  2012cited by this paper
• A simple and effective weighted phrase extraction for machine translation adaptation

  2012cited by this paper
• Topic Models for Dynamic Translation Model Adaptation

  2012cited by this paper
• Approximate Sentence Retrieval for Scalable and Efficient Example-Based Machine Translation

  2012cited by this paper
• A Joint Chinese Named Entity Recognition and Disambiguation System

  2012cited by this paper
• FreeLing 3.0: Towards Wider Multilinguality

  2012cited by this paper
• TQDL: Integrated Models for Cross-Language Document Retrieval

  2012cited by this paper
• Automatic acquisition of named entities for rule-based machine translation

  2011cited by this paper
• Domain Adaptation for Machine Translation by Mining Unseen Words

  2011cited by this paper
• Towards Using Web-Crawled Data for Domain Adaptation in Statistical Machine Translation

  2011cited by this paper
• DOCUMENT TRANSLATION RETRIEVAL BASED ON STATISTICAL MACHINE TRANSLATION TECHNIQUES

  2011cited by this paper
• Experiments on Domain Adaptation for Patent Machine Translation in the PLuTO project

  2011cited by this paper
• Training Machine Translation with a Second-Order Taylor Approximation of Weighted Translation Instances

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

  2011influential reference
• KenLM: Faster and Smaller Language Model Queries

  2011cited by this paper
• MultiUN: A Multilingual Corpus from United Nation Documents

  2010influential reference
• TectoMT: Modular NLP Framework

  2010cited by this paper
• Lingua-Align: An Experimental Toolbox for Automatic Tree-to-Tree Alignment

  2010cited by this paper
• Convergence of Translation Memory and Statistical Machine Translation

  2010cited by this paper
• Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation

  2010cited by this paper
• Intelligent Selection of Language Model Training Data

  2010influential reference
• Feature-Rich Discriminative Phrase Rescoring for SMT

  2010cited by this paper
• Boilerplate detection using shallow text features

  2010cited by this paper
• Master's Thesis Institute of Formal and Applied Linguistics

  2010cited by this paper
• Combining Content-Based and URL-Based Heuristics to Harvest Aligned Bitexts from Multilingual Sites with Bitextor

  2010cited by this paper
• Discriminative Corpus Weight Estimation for Machine Translation

  2009cited by this paper
• News from OPUS — A collection of multilingual parallel corpora with tools and interfaces

  2009cited by this paper
• Web page classification: Features and algorithms

  2009cited by this paper
• Sentence Boundary Detection and the Problem with the U.S.

  2009influential reference
• Domain Adaptation for Statistical Machine Translation with Monolingual Resources

  2009cited by this paper
• WeBiText: Building Large Heterogeneous Translation Memories from Parallel Web Content

  2008influential reference
• Parallel Implementations of Word Alignment Tool

  2008influential reference
• IRSTLM: an open source toolkit for handling large scale language models

  2008influential reference
• Investigations on large-scale lightly-supervised training for statistical machine translation.

  2008cited by this paper
• Mixture-Model Adaptation for SMT

  2007cited by this paper
• Factored Translation Models

  2007cited by this paper
• Capturing practical natural language transformations

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

  2007influential reference
• Transductive learning for statistical machine translation

  2007cited by this paper
• Domain Adaptation in Statistical Machine Translation with Mixture Modelling

  2007cited by this paper
• Comprehensive Survey on Distance/Similarity Measures between Probability Density Functions

  2007cited by this paper
• Improving Statistical Machine Translation Performance by Training Data Selection and Optimization

  2007influential reference
• Word-Based Alignment, Phrase-Based Translation: What’s the Link?

  2006cited by this paper
• Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics

  2006cited by this paper
• Automatic Acquisition of Chinese-English Parallel Corpus from the Web

  2006cited by this paper
• Dependency treelet translation: the convergence of statistical and example-based machine-translation?

  2006cited by this paper
• Comparing example-based and statistical machine translation

  2005cited by this paper
• Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling

  2005cited by this paper
• Adaptation of the translation model for statistical machine translation based on information retrieval

  2005cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005influential reference
• PEBL: Web page classification without negative examples

  2004cited by this paper
• Example-based controlled translation

  2004cited by this paper
• Modelling highly inflected languages

  2004cited by this paper
• The Alignment Template Approach to Statistical Machine Translation

  2004cited by this paper
• Language Model Adaptation for Statistical Machine Translation via Structured Query Models

  2004cited by this paper
• Building parallel corpora by automatic title alignment using length-based and text-based approaches

  2004cited by this paper
• Discovering Parallel Text from the World Wide Web

  2004cited by this paper
• Effective Phrase Translation Extraction from Alignment Models

  2003cited by this paper
• Chunk-Based Statistical Translation

  2003cited by this paper
• Minimum Error Rate Training in Statistical Machine Translation

  2003influential reference

• Improving Language Model Integration for Neural Machine Translation

  2023cites this paper
• Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging

  2021cites this paper
• Joint Training for Neural Machine Translation

  2019cites this paper
• What Level of Quality can Neural Machine Translation Attain on Literary Text?

  2018cites this paper
• Parallel fragments : Measuring their impact on translation performance

  2017cites this paper
• Building Multiword Expressions Bilingual Lexicons for Domain Adaptation of an Example-Based Machine Translation System

  2017cites this paper
• Building a Neural Machine Translation System Using Only Synthetic Parallel Data

  2017cites this paper
• Semi-Supervised Learning for Neural Machine Translation

  2016influential citation