Compounds

While the words in English compounds such as machine translation remain separate, others merge them into a single new word, a highly productive process that leads to large vocabulary sizes.

Compounds is the main subject of 22 publications. 18 are discussed here.

Publications

Translating from compounding languages like German requires compound splitting methods (Brown, 2002). A frequency-based method, supported by linguistic clues is introduced by Koehn and Knight (2003). This method is refined by Stymne (2008), such as by addressing more of the morphological changes that occur due to compounding. Macherey et al. (2011) learn the required morphological changes. Compound splitting can also be provided by morphological analysers (Nießen and Ney, 2000; Holmqvist et al., 2007). Fritzinger and Fraser (2010) combine linguistic analysis with corpus-driven statistics. Weller et al. (2014) also consider the semantic similarity (using distributional models) between the compound and its potential parts to guide splitting decisions. Since there are multiple ways to split potential compounds, Dyer (2009) provides multiple splits to the decoder in an input lattice. Wuebker and Ney (2012) consider multiple splits also during phrase model training. When translating into compounding languages, compounds have to be generated. Stymne et al. (2013) provide an extensive overview. Popovic et al. (2006) split compounds during training and merge them in post-processing. Stymne et al. (2008) also allow the creation of novel words by compounding. Stymne (2009) compares various methods to mark split points, and consider the part of speech of split words. Stymne and Cancedda (2011) extend this approach further by a Conditional Random Field (CRF) classifier that detects merge points. This work was integrated by Fraser et al. (2012) as a post-processing step into a machine translation system. Armed with both a corpus based approach and a morphological analyzer to split words, Cap et al. (2014) build a CRF classifier for merge points that also includes features about the source language, such as that the two words are part of the same base noun phrase. Botha et al. (2012) develop a hierarchical Pitman-Yor language model to better handle compounds.

Benchmarks

Discussion

Related Topics

New Publications

• Cap, Fabienne and Nirmal, Manju and Weller, Marion and Schulte im Walde, Sabine (2015): How to Account for Idiomatic German Support Verb Constructions in Statistical Machine Translation, Proceedings of the 11th Workshop on Multiword Expressions

  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{cap-EtAl:2015:MWE,
  author = {Cap, Fabienne and Nirmal, Manju and Weller, Marion and Schulte im Walde, Sabine},
  title = {How to Account for Idiomatic {German} Support Verb Constructions in Statistical Machine Translation},
  booktitle = {Proceedings of the 11th Workshop on Multiword Expressions},
  month = {June},
  address = {Denver, Colorado},
  publisher = {Association for Computational Linguistics},
  pages = {19--28},
  url = {http://www.aclweb.org/anthology/W15-0903},
  year = 2015
  }
  Cap et al. (2015)
• Matthews, Austin and Schlinger, Eva and Lavie, Alon and Dyer, Chris (2016): Synthesizing Compound Words for Machine Translation, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

  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{matthews-EtAl:2016:P16-1,
  author = {Matthews, Austin and Schlinger, Eva and Lavie, Alon and Dyer, Chris},
  title = {Synthesizing Compound Words for Machine Translation},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month = {August},
  address = {Berlin, Germany},
  publisher = {Association for Computational Linguistics},
  pages = {1085--1094},
  url = {http://www.aclweb.org/anthology/P16-1103},
  year = 2016
  }
  Matthews et al. (2016)
• Marcin Junczys-Dowmunt and Bruno Pouliquen (2014): SMT of German patents at WIPO: decompounding and verb structure pre-reordering, Proceedings of 17th Annual conference of the European Association for Machine Translation mentioned in Deployment and Compounds

  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{eamt-2014-Junczyns-Dowmunt,
  author = {Marcin Junczys-Dowmunt and Bruno Pouliquen},
  title = {SMT of {German} patents at WIPO: decompounding and verb structure pre-reordering},
  booktitle = {Proceedings of 17th Annual conference of the European Association for Machine Translation},
  pages = {217-220},
  url = {http://www.mt-archive.info/10/EAMT-2014-Junczyns-Dowmunt.pdf},
  location = {Dubrovnik, Croatia},
  year = 2014
  }
  Junczys-Dowmunt and Pouliquen (2014)
• Pu, Xiao and Mascarell, Laura and Popescu-Belis, Andrei and Fishel, Mark and Luong, Ngoc-Quang and Volk, Martin (2015): Leveraging Compounds to Improve Noun Phrase Translation from Chinese and German, Proceedings of the ACL-IJCNLP 2015 Student Research Workshop

  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{pu-EtAl:2015:SRW,
  author = {Pu, Xiao and Mascarell, Laura and Popescu-Belis, Andrei and Fishel, Mark and Luong, Ngoc-Quang and Volk, Martin},
  title = {Leveraging Compounds to Improve Noun Phrase Translation from {Chinese} and German},
  booktitle = {Proceedings of the ACL-IJCNLP 2015 Student Research Workshop},
  month = {July},
  address = {Beijing, China},
  publisher = {Association for Computational Linguistics},
  pages = {8--15},
  url = {http://www.aclweb.org/anthology/P15-3002},
  year = 2015
  }
  Pu et al. (2015)