Vector Space Models for Phrase-based Machine Translation

This paper investigates the application of vector space models (VSMs) to the standard phrase-based machine translation pipeline. VSMs are models based on continuous word representations embedded in a vector space. We exploit word vectors to augment the phrase table with new inferred phrase pairs. This helps reduce out-of-vocabulary (OOV) words. In addition, we present a simple way to learn bilingually-constrained phrase vectors. The phrase vectors are then used to provide additional scoring of phrase pairs, which fits into the standard log-linear framework of phrase-based statistical machine translation. Both methods result in significant improvements over a competitive in-domain baseline applied to the Arabic-to-English task of IWSLT 2013.

• Publication year

  2014

• Venue

  SSST@EMNLP

• Publication date

  2014-10-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/v1/W14-4001
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Hallucinating Phrase Translations for Low Resource MT

  2014cited by this paper
• Fast and Robust Neural Network Joint Models for Statistical Machine Translation

  2014cited by this paper
• Minimum Translation Modeling with Recurrent Neural Networks

  2014cited by this paper
• Translation Modeling with Bidirectional Recurrent Neural Networks

  2014cited by this paper
• Bilingually-constrained Phrase Embeddings for Machine Translation

  2014cited by this paper
• An Introduction to Information Retrieval

  2013cited by this paper
• Bilingual Word Embeddings for Phrase-Based Machine Translation

  2013cited by this paper
• Exploiting Similarities among Languages for Machine Translation

  2013influential reference
• Learning Semantic Representations for the Phrase Translation Model

  2013cited by this paper
• Recurrent Continuous Translation Models

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

  2013cited by this paper
• Jane 2: Open Source Phrase-based and Hierarchical Statistical Machine Translation

  2012cited by this paper
• Toward Statistical Machine Translation without Parallel Corpora

  2012cited by this paper
• Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability

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

  2010cited by this paper
• Bilingual Sense Similarity for Statistical Machine Translation

  2010cited by this paper
• Jane: Open Source Hierarchical Translation, Extended with Reordering and Lexicon Models

  2010cited by this paper
• From Frequency to Meaning: Vector Space Models of Semantics

  2010cited by this paper
• Improved Statistical Machine Translation Using Monolingually-Derived Paraphrases

  2009cited by this paper
• A unified architecture for natural language processing: deep neural networks with multitask learning

  2008cited by this paper
• A Simple and Effective Hierarchical Phrase Reordering Model

  2008cited by this paper
• Continuous space language models

  2007cited by this paper
• A Systematic Comparison of Various Statistical Alignment Models

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

  2003cited by this paper
• A Neural Probabilistic Language Model

  2003cited by this paper
• SRILM - an extensible language modeling toolkit

  2002cited by this paper
• Discriminative Training and Maximum Entropy Models for Statistical Machine Translation

  2002cited by this paper
• A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.

  1997cited by this paper
• Producing high-dimensional semantic spaces from lexical co-occurrence

  1996cited by this paper
• Distributional Structure

  1954cited by this paper

• Language Models Are Implicitly Continuous

  2025cites this paper
• Extracting the essence

  2019cites this paper
• Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies

  2019cites this paper
• PERSPECTIVES OF ARABIC MACHINE TRANSLATION

  2017cites this paper
• Improving Phrase-Based SMT Using Cross-Granularity Embedding Similarity

  2016influential citation
• Alignment-Based Neural Machine Translation

  2016cites this paper
• Using Word Embeddings for Improving Statistical Machine Translation of Phrasal Verbs

  2016cites this paper
• Deliverable D 1 . 5 Improved Learning for Machine Translation

  2016cites this paper
• Improving Statistical Machine Translation with a Multilingual Paraphrase Database

  2015cites this paper
• Modelling Syntactic and Semantic Tasks with Linguistically Enriched Recursive Neural Networks

  2015cites this paper
• Bilingual distributed phrase representations for statistical machin translation

  2015cites this paper