The Karlsruhe Institute of Technology Translation Systems for the WMT 2014

In this paper, we present the KIT systems participating in the Shared Translation Task translating between English$German and English$French. All translations are generated using phrase-based translation systems, using different kinds of word-based, part-ofspeech-based and cluster-based language models trained on the provided data. Additional models include bilingual language models, reordering models based on part-of-speech tags and syntactic parse trees, as well as a lexicalized reordering model. In order to make use of noisy web-crawled data, we apply filtering and data selection methods for language modeling. A discriminative word lexicon using source context information proved beneficial for all translation directions.

• Publication year

  2014

• Venue

  WMT@ACL

• Publication date

  2014-06-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/v1/W14-3313
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An MT Error-Driven Discriminative Word Lexicon using Sentence Structure Features

  2013cited by this paper
• Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation

  2013cited by this paper
• The KIT translation systems for IWSLT 2012

  2012cited by this paper
• Parallel Phrase Scoring for Extra-large Corpora

  2012influential reference
• Detailed Analysis of Different Strategies for Phrase Table Adaptation in SMT

  2012cited by this paper
• KenLM: Faster and Smaller Language Model Queries

  2011cited by this paper
• The KIT English-French translation systems for IWSLT 2011

  2011influential reference
• Using Wikipedia to translate domain-specific terms in SMT

  2011cited by this paper
• Wider Context by Using Bilingual Language Models in Machine Translation

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

  2010cited by this paper
• Extending Statistical Machine Translation with Discriminative and Trigger-Based Lexicon Models

  2009cited by this paper
• A POS-Based Model for Long-Range Reorderings in SMT

  2009cited by this paper
• Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging

  2008cited by this paper
• Discriminative Word Alignment via Alignment Matrix Modeling

  2008cited by this paper
• Parsing Three German Treebanks: Lexicalized and Unlexicalized Baselines

  2008cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• Word reordering in statistical machine translation with a POS-based distortion model

  2007cited by this paper
• Phrasetable Smoothing for Statistical Machine Translation

  2006cited by this paper
• Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation

  2005cited by this paper
• Accurate Unlexicalized Parsing

  2003cited by this paper
• Empirical Methods for Compound Splitting

  2003cited by this paper
• SMT decoder dissected: word reordering

  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

  2002cited by this paper
• SRILM - an extensible language modeling toolkit

  2002cited by this paper
• An Efficient Method for Determining Bilingual Word Classes

  1999cited by this paper
• Probabilistic part-of-speech tagging using decision trees

  1994cited by this paper

• Multilingual Neural Translation

  2020cites this paper
• Towards a Map of the Syntactic Similarity of Languages

  2017cites this paper
• Extracting translation pairs from social network content

  2014cites this paper
• Findings of the 2014 Workshop on Statistical Machine Translation

  2014cites this paper
• EU-BRIDGE MT: Combined Machine Translation

  2014cites this paper
• Combining techniques from different NN-based language models for machine translation

  2014influential citation
• Adaptation in Machine Translation

  2014cites this paper
• Anaphora Models and Reordering for Phrase-Based SMT

  2014cites this paper
• Findings of the 2013 Workshop on Statistical Machine Translation

  2013cites this paper
• Discourse in Statistical Machine Translation

  2012cites this paper
• Getting Bilingual Information from the Web

  2012cites this paper