But Dictionaries Are Data Too

Although empiricist approaches to machine translation depend vitally on data in the form of large bilingual corpora, bilingual dictionaries are also a source of information. We show how to model at least a part of the information contained in a bilingual dictionary so that we can treat a bilingual dictionary and a bilingual corpus as two facets of a unified collection of data from which to extract values for the parameters of a probabilistic machine translation system. We give an algorithm for obtaining maximum likelihood estimates of the parameters of a probabilistic model from this combined data and we show how these parameters are affected by inclusion of the dictionary for some sample words.

• Publication year

  1993

• Venue

  Human Language Technology - The Baltic Perspectiv

• Publication date

  1993-03-21

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1075671.1075716
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The Mathematics of Statistical Machine Translation: Parameter Estimation

  1993cited by this paper
• Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

  1977cited by this paper
• An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process

  1972cited by this paper

• Training on Lexical Resources

  2022cites this paper
• Neural Baselines for Word Alignment

  2020cites this paper
• Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models

  2019cites this paper
• Integrating Rules and Dictionaries from Shallow-Transfer Machine Translation into Phrase-Based Statistical Machine Translation

  2016cites this paper
• Smoothing the parameter of IBM word alignment models: the framework and its learning approaches

  2016influential citation
• Smoothing parameter estimation framework for IBM word alignment models

  2016cites this paper
• Using Parallel Texts and Lexicons for Verbal Word Sense Disambiguation

  2015influential citation
• Leave-one-out Word Alignment without Garbage Collector Effects

  2015influential citation
• Building machine translation systems for language pairs with scarce resources

  2015influential citation
• Parallel Text Ranking for Cleaning Up Translation Memory

  2015cites this paper
• Posterior Regularization for Structured Latent Varaible Models

  2015influential citation
• Predicate Argument Alignment using a Global Coherence Model

  2015cites this paper
• Improving Word Alignment Through Morphological Analysis

  2015cites this paper
• Translation-based ranking in cross-language information retrieval

  2014cites this paper
• Chapter 4 An Open-Source Toolkit for Integrating Shallow-Transfer Rules into Phrase-Based Statistical Machine Translation

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

  2013cites this paper
• Cross-Lingual Discriminative Learning of Sequence Models with Posterior Regularization

  2013cites this paper
• Beyond Bitext: Five Open Problems in Machine Translation

  2013cites this paper
• Generalizing sampling-based multilingual alignment

  2013cites this paper
• When multiwords go bad in machine translation

  2013cites this paper
• Getting Past the Language Gap: Innovations in Machine Translation

  2013cites this paper
• Improving Statistical Machine Translation Using Bayesian Word Alignment and Gibbs Sampling

  2013cites this paper
• The TÜBİTAK statistical machine translation system for IWSLT 2012

  2012cites this paper
• An open-source toolkit for integrating shallow-transfer rules into phrase-based statistical machine translation

  2012cites this paper
• Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages

  2012influential citation
• 1 An Open-Source Toolkit for Integrating Shallow-Transfer Rules into Phrase-Based Statistical Machine Translation

  2012cites this paper
• Evaluation of a Bilingual Dictionary Extracted from Wikipedia

  2012cites this paper
• Posterior Regularization Framework : Learning Tractable Models with Intractable Constraints

  2011influential citation
• Enriching a statistical machine translation system trained on small parallel corpora with rule-based bilingual phrases

  2011cites this paper
• Angelina Ivanova Creating a Bilingual Dictionary using Wikipedia

  2011cites this paper
• Integrating shallow-transfer rules into phrase-based statistical machine translation

  2011cites this paper
• The Universitat d’Alacant hybrid machine translation system for WMT 2011

  2011cites this paper
• Probabilistic Word Alignment under the L_0-norm

  2011cites this paper
• Towards Language Independent NE Identification in the context of Wikipedia

  2010cites this paper
• Posterior Regularization for Structured Latent Variable Models

  2010influential citation
• Learning Tractable Word Alignment Models with Complex Constraints

  2010influential citation
• On the mono- and cross-language detection of text reuse and plagiarism

  2010cites this paper
• Posterior Regularization for Learning with Side Information and Weak Supervision

  2010influential citation
• PostCAT - Posterior Constrained Alignment Toolkit

  2009cites this paper
• SMT and SPE Machine Translation Systems for WMT‘09

  2009cites this paper
• Improved Statistical Machine Translation for Resource-Poor Languages Using Related Resource-Rich Languages

  2009cites this paper
• A prototype English-Turkish statistical machine translation system (İngilizce-Türkçe istatistiksel bilgisayarlı çeviri sistemi prototipi)

  2009cites this paper
• A novel alignment model inspired on IBM Model 1

  2008cites this paper
• Better Alignments = Better Translations?

  2008cites this paper
• Learning for semantic parsing and natural language generation using statistical machine translation techniques

  2007influential citation
• Expectation Maximization and Posterior Constraints

  2007cites this paper
• Aligning Turkish and English Parallel Texts for Statistical Machine Translation

  2005cites this paper
• Constrained EM for parallel text alignment

  2005cites this paper
• Exploiting phrasal lexica and additional morpho-syntactic language resources for statistical machine translation with scarce training data

  2005cites this paper
• Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information

  2004cites this paper
• Improving IBM Word Alignment Model 1

  2004influential citation
• A Systematic Comparison of Various Statistical Alignment Models

  2003influential citation
• Statistical machine translation: from single word models to alignment templates

  2002cites this paper
• Improving a general-purpose Statistical Translation Engine by Terminological lexicons

  2002cites this paper
• An Intelligent Terminology Database as a Pre-processor for Statistical Machine Translation

  2002cites this paper
• Opening Statistical Translation Engines to Terminological Resources

  2002cites this paper
• Improving statistical machine translation using morpho-syntactic information

  2002cites this paper
• Detection of Translational Equivalence

  2001cites this paper
• Toward hierarchical models for statistical machine translation of inflected languages

  2001cites this paper
• Statistical machine learning for information retrieval

  2001cites this paper
• Improved Statistical Alignment Models

  2000cites this paper
• Models of translation equivalence among words

  2000influential citation
• Information retrieval as statistical translation

  1999cites this paper
• Statistical Machine Translation: Final Report

  1999cites this paper
• Information Retrieval and Information Theory

  1999cites this paper
• Word-to-Word Models of Translational Equivalence

  1998cites this paper
• Automating Knowledge Acquisition for Machine Translation

  1997cites this paper
• A Word-to-Word Model of Translational Equivalence

  1997cites this paper
• Combining corpus and machine-readable dictionary data for building bilingual lexicons

  1995cites this paper
• Automatic Evaluation and Uniform Filter Cascades for Inducing N-Best Translation Lexicons

  1995influential citation
• Inducing Concatenative Units from Machine Readable Dictionaries and Corporafor Speech

  1994cites this paper
• Word Sense Disambiguation Using a Second Language Monolingual Corpus

  1994cites this paper
• A Monografie

  year unknowncites this paper