Symmetrization

The birth defect of the IBM Models is the restriction to one-to-many alignments. Training models in both directions, and merging the outcome of the training overcomes this.

Symmetrization is the main subject of 12 publications. 10 are discussed here.

Publications

Symmetrizing IBM model alignments was first proposed by Och and Ney (2003) and may be improved by already symmetrizing during the IBM Model training (Matusov et al., 2004), or by explicitly modeling the agreement between the two alignments and optimizing it during with EM training (Liang et al., 2006). Different word alignments obtained with various IBM Models and symmetrization methods may also be combined using a maximum entropy approach (Ayan and Dorr, 2006; Ganchev et al., 2008). Crego and Habash (2008) use constraints over syntactic chunks to guide symmetrization. Starting an word alignment resulting from IBM models, additional features may be defined to assess each alignment points. Fraser and Marcu (2006) use additional features during symmetrization, either to be used in re-ranking or integrated into the search. Such features may form the basis for a classifier that adds one alignment points at at time (Ren et al., 2007), possibly based on a skeleton of highly likely alignment points (Ma et al., 2008), or deletes alignment points one at a time from the symmetrized union alignment (Fossum et al., 2008).

Benchmarks

Discussion

Related Topics

New Publications

• Liu, Chunyang and Liu, Yang and Sun, Maosong and Luan, Huanbo and Yu, Heng (2015): Generalized Agreement for Bidirectional Word Alignment, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

  DELETEIntroduction   ResearchGroups   AvailableSoftware   SpeechTranslation   SignLanguage   ComputerAidedTranslation   OtherApproaches   Deployment Data   ParallelCorpora   ComparableCorpora   Dictionaries   CorpusCleaning   SentenceAlignment   Truecasing   WordSegmentation   SpellingCorrection   SparseData   PivotLanguages   DomainAdaptation WordBasedModels   IBMModels   Symmetrization   WordAlignment     WordAlignmentBasedOnCoocurrence     WordAlignmentWithLinguisticAnnotation     WordAlignmentForSyntaxBasedModels     DiscriminativeWordAlignment     WordAlignmentCombination     WordAlignmentEvaluation     AlignmentOfSubsententialUnits   DictionariesFromComparableCorpora   LexicalChoice   MTWithoutWordAlignment PhraseBasedModels   PhraseBasedModelTraining   PhraseBasedModelEM   PhraseBasedModelRefinement   ContextFeatures   Smoothing   Paraphrasing   PruningLargeModels   SuffixArrays   ReorderingModels   PhraseBasedVsEBMT SyntaxBasedModels   InversionTransductionGrammars   HierarchicalModels   StringToTree   TreeToString   TreeToTree   BinarizingSCFG   GenerativeSyntaxModels   DependencyStructure   DeepSyntax   ParseQuality   ParallelTreebanks   SyntacticCoherence LinguisticProblems   UnknownWords   Morphology   GeneratingRichMorphology   FactoredTranslationModels   Compounds   TranslatingTenseCaseMarkers   TranslatingChunksAndClauses   DocumentLevelAspects   Transliteration     TransliterationWithFSM     TransliterationWithOtherMethods     ForwardTransliteration     TransliterationTrainingData     IntegratingTransliteration   SyntacticPrereordering   POSChunkPrereordering   SyntacticReranking   IntegratingSyntacticFeatures LanguageModels   NGramLanguageModels   TargetedLanguageModels   MorphologicalLanguageModels   VeryLargeLanguageModels Decoding   StackDecoding   ReorderingConstraints   WordBasedDecoding   FiniteStateMachines   DecodingComplexity   SyntaxModelDecoding Evaluation   EvaluationCampaigns   ManualMetrics   TaskBasedMetrics   EditRateMetrics   NGramMetrics   SyntaxBasedMetrics   CorrelationOfMetrics   TrainedMetrics   TranslationDifficulty   StatisticalSignificance MachineLearning   WordGraphs   ParameterTuning   Reranking   LargeScaleDiscriminativeTraining   MinimumBayesRisk   ConfidenceMeasures   SystemCombination   IncrementalUpdating NeuralNetworkModels   NeuralLanguageModels   AttentionModel   Training   Inference   Coverage   Vocabulary   Embeddings   MultilingualWordEmbeddings   MonolingualData   Adaptation   LinguisticAnnotation   MultilingualMultimodalMultitask   AlternativeArchitectures   AnalysisAndVisualization   NeuralComponentsInStatisticalMachineTranslation add

  

  @InProceedings{liu-EtAl:2015:EMNLP1,
  author = {Liu, Chunyang and Liu, Yang and Sun, Maosong and Luan, Huanbo and Yu, Heng},
  title = {Generalized Agreement for Bidirectional Word Alignment},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  month = {September},
  address = {Lisbon, Portugal},
  publisher = {Association for Computational Linguistics},
  pages = {1828--1836},
  url = {http://aclweb.org/anthology/D15-1210},
  year = 2015
  }
  Liu et al. (2015)
• Brown, Ralf D. and Kim, Jae Dong and Jansen, Peter J. and Carbonell, Jaime G. (2005): Symmetric Probabilistic Alignment, Proceedings of the ACL Workshop on Building and Using Parallel Texts

  DELETEIntroduction   ResearchGroups   AvailableSoftware   SpeechTranslation   SignLanguage   ComputerAidedTranslation   OtherApproaches   Deployment Data   ParallelCorpora   ComparableCorpora   Dictionaries   CorpusCleaning   SentenceAlignment   Truecasing   WordSegmentation   SpellingCorrection   SparseData   PivotLanguages   DomainAdaptation WordBasedModels   IBMModels   Symmetrization   WordAlignment     WordAlignmentBasedOnCoocurrence     WordAlignmentWithLinguisticAnnotation     WordAlignmentForSyntaxBasedModels     DiscriminativeWordAlignment     WordAlignmentCombination     WordAlignmentEvaluation     AlignmentOfSubsententialUnits   DictionariesFromComparableCorpora   LexicalChoice   MTWithoutWordAlignment PhraseBasedModels   PhraseBasedModelTraining   PhraseBasedModelEM   PhraseBasedModelRefinement   ContextFeatures   Smoothing   Paraphrasing   PruningLargeModels   SuffixArrays   ReorderingModels   PhraseBasedVsEBMT SyntaxBasedModels   InversionTransductionGrammars   HierarchicalModels   StringToTree   TreeToString   TreeToTree   BinarizingSCFG   GenerativeSyntaxModels   DependencyStructure   DeepSyntax   ParseQuality   ParallelTreebanks   SyntacticCoherence LinguisticProblems   UnknownWords   Morphology   GeneratingRichMorphology   FactoredTranslationModels   Compounds   TranslatingTenseCaseMarkers   TranslatingChunksAndClauses   DocumentLevelAspects   Transliteration     TransliterationWithFSM     TransliterationWithOtherMethods     ForwardTransliteration     TransliterationTrainingData     IntegratingTransliteration   SyntacticPrereordering   POSChunkPrereordering   SyntacticReranking   IntegratingSyntacticFeatures LanguageModels   NGramLanguageModels   TargetedLanguageModels   MorphologicalLanguageModels   VeryLargeLanguageModels Decoding   StackDecoding   ReorderingConstraints   WordBasedDecoding   FiniteStateMachines   DecodingComplexity   SyntaxModelDecoding Evaluation   EvaluationCampaigns   ManualMetrics   TaskBasedMetrics   EditRateMetrics   NGramMetrics   SyntaxBasedMetrics   CorrelationOfMetrics   TrainedMetrics   TranslationDifficulty   StatisticalSignificance MachineLearning   WordGraphs   ParameterTuning   Reranking   LargeScaleDiscriminativeTraining   MinimumBayesRisk   ConfidenceMeasures   SystemCombination   IncrementalUpdating NeuralNetworkModels   NeuralLanguageModels   AttentionModel   Training   Inference   Coverage   Vocabulary   Embeddings   MultilingualWordEmbeddings   MonolingualData   Adaptation   LinguisticAnnotation   MultilingualMultimodalMultitask   AlternativeArchitectures   AnalysisAndVisualization   NeuralComponentsInStatisticalMachineTranslation add

  

  @InProceedings{brown-EtAl:2005:WPT,
  author = {Brown, Ralf D. and Kim, Jae Dong and Jansen, Peter J. and Carbonell, Jaime G.},
  title = {Symmetric Probabilistic Alignment},
  booktitle = {Proceedings of the ACL Workshop on Building and Using Parallel Texts},
  month = {June},
  address = {Ann Arbor, Michigan},
  publisher = {Association for Computational Linguistics},
  pages = {87--90},
  url = {http://www.aclweb.org/anthology/W/W05/W05-0813},
  year = 2005
  }
  Brown et al. (2005)