Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Related Work
Morphology Projection Hypothesis
Learning Procedure
Conclusion
References
All Topics
Computer Science
Artificial Intelligence

Machine translation with source-predicted target morphology

Profile image of Khalil Sima'anKhalil Sima'an

2015

Abstract

We propose a novel pipeline for translation into morphologically rich languages which consists of two steps: initially, the source string is enriched with target morphological features and then fed into a translation model which takes care of reordering and lexical choice that matches the provided morphological features. As a proof of concept we first show improved translation performance for a phrase-based model translating source strings enriched with morphological features projected through the word alignments from target words to source words. Given this potential, we present a model for predicting target morphological features on the source string and its predicate-argument structure, and tackle two major technical challenges: (1) How to fit the morphological feature set to training data? and (2) How to integrate the morphology into the back-end phrase-based model such that it can also be trained on projected (rather than predicted) features for a more efficient pipeline? For the ...

Related papers

Improving the Performance of Neural Machine Translation Involving Morphologically Rich Languages
Hans Krupakar

ArXiv, 2016

The advent of the attention mechanism in neural machine translation models has improved the performance of machine translation systems by enabling selective lookup into the source sentence. In this paper, the efficiencies of translation using bidirectional encoder attention decoder models were studied with respect to translation involving morphologically rich languages. The English - Tamil language pair was selected for this analysis. First, the use of Word2Vec embedding for both the English and Tamil words improved the translation results by 0.73 BLEU points over the baseline RNNSearch model with 4.84 BLEU score. The use of morphological segmentation before word vectorization to split the morphologically rich Tamil words into their respective morphemes before the translation, caused a reduction in the target vocabulary size by a factor of 8. Also, this model (RNNMorph) improved the performance of neural machine translation by 7.05 BLEU points over the RNNSearch model used over the ...

View PDFchevron_right
Translating from Morphologically Complex Languages: A Paraphrase-Based Approach
Preslav Nakov

We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we treat as potential paraphrases and handle using paraphrasing techniques at the word, phrase, and sentence level. An important advantage of this framework is that it can cope with derivational morphology, which has so far remained largely beyond the capabilities of statistical machine translation systems. Our experiments translating from Malay, whose morphology is mostly derivational, into English show significant improvements over rivaling approaches based on five automatic evaluation measures (for 320,000 sentence pairs; 9.5 million English word tokens).

View PDFchevron_right
Enriching Morphologically Poor Languages for Statistical Machine Translation
Eleftherios Avramidis

2008

We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the syntax of the source sentence to extract information for noun cases and verb persons and annotate the corresponding words accordingly. In experiments, we show improved performance for translating from English into Greek and Czech. For English-Greek, we reduce the error on the verb conjugation from 19% to 5.4% and noun case agreement from 9% to 6%.

View PDFchevron_right
Morphological analysis for statistical machine translation
jaden wu

Proceedings of HLT-NAACL 2004: Short Papers, 2004

We present a novel morphological analysis technique which induces a morphological and syntactic symmetry between two languages with highly asymmetrical morphological structures to improve statistical machine translation qualities. The technique pre-supposes fine-grained segmentation of a word in the morphologically rich language into the sequence of prefix(es)-stem-suffix(es) and part-of-speech tagging of the parallel corpus.

View PDFchevron_right
End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages
João Paulo de Souza Aires

ArXiv, 2021

Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. In particular, we focus on methods based on training the model with constraints provided as part of the input sequence. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained terms in both automatic and manual evaluation by reducing errors in agreement. Our approach thus eliminates inflection errors, without introducing...

View PDFchevron_right
Hybrid Morphological Segmentation for Phrase-Based Machine Translation
Mikko Kurimo

Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016

This article describes the Aalto University entry to the English-to-Finnish news translation shared task in WMT 2016. Our segmentation method combines the strengths of rule-based and unsupervised morphology. We also attempt to correct errors in the boundary markings by post-processing with a neural morph boundary predictor.

View PDFchevron_right
Modelling linguistic phenomena with unsupervised morphology for improving statistical machine translation
Mark Fishel

2008

View PDFchevron_right
Enhancing morphological alignment for translating highly inflected languages
Min-Yen Kan

2010

Abstract We propose an unsupervised approach utilizing only raw corpora to enhance morphological alignment involving highly inflected languages. Our method focuses on closed-class morphemes, modeling their influence on nearby words. Our language-independent model recovers important links missing in the IBM Model 4 alignment and demonstrates improved end-to-end translations for English-Finnish and English-Hungarian.

View PDFchevron_right
Automatic Construction of Morphologically Motivated Translation Models for Highly Inflected, Low-Resource Languages
David Yarowsky

2016

Statistical Machine Translation (SMT) of highly inflected, low-resource languages suffers from the problem of low bitext availability, which is exacerbated by large inflectional paradigms. When translating into English, rich source inflections have a high chance of being poorly estimated or out-of-vocabulary (OOV). We present a source language-agnostic system for automatically constructing phrase pairs from foreign-language inflections and their morphological analyses using manually constructed datasets, including Wiktionary. We then demonstrate the utility of these phrase tables in improving translation into English from Finnish, Czech, and Turkish in simulated low-resource settings, finding substantial gains in translation quality. We report up to +2.58 BLEU in a simulated low-resource setting and +1.65 BLEU in a moderateresource setting. We release our morphologically-motivated translation models, with tens of thousands of inflections in each of 8 languages.

View PDFchevron_right
Addressing data sparsity for neural machine translation between morphologically rich languages
Walid Aransa

Machine Translation, 2020

Translating between morphologically rich languages is still challenging for actual machine translation systems. In this paper, we experiment with various Neural Machine Translation (NMT) architectures to address the data sparsity problem caused by data availability (quantity), domain shift and the languages involved (Arabic and French). We showed that the Factored NMT (FNMT) model, which uses linguistically motivated factors, is able to outperform standard NMT systems using subword units by more than 1% BLEU point even when a large quantity of data is available. Our work shows the benefits of applying linguistic factors in NMT when faced with low and large resource conditions.

View PDFchevron_right

References (29)

  1. Avramidis, E. and Koehn, P. (2008). Enriching morphologically poor languages for statistical machine translation. In Proceedings of ACL-08: HLT, pages 763-770, Columbus, Ohio. Association for Computational Linguistics.
  2. Bojar, O. and Kos, K. (2010). 2010 failures in English-Czech phrase-based MT. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, WMT '10, pages 60-66, Stroudsburg, PA, USA. Association for Computational Linguistics.
  3. Brown, P. F., Pietra, V. J. D., Pietra, S. A. D., and Mercer, R. L. (1993). The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2):263- 311.
  4. Cap, F., Fraser, A., Weller, M., and Cahill, A. (2014a). How to produce unseen teddy bears: Improved morphological processing of compounds in SMT. In Proceedings of the 14th Con- ference of the European Chapter of the Association for Computational Linguistics, pages 579-587, Gothenburg, Sweden. Association for Computational Linguistics.
  5. Cap, F., Weller, M., Ramm, A., and Fraser, A. (2014b). CimS -the CIS and IMS joint sub- mission to WMT 2014 translating from English into German. In Proceedings of the Ninth Workshop on Statistical Machine Translation, pages 71-78, Baltimore, Maryland, USA. As- sociation for Computational Linguistics.
  6. Carpuat, M. and Wu, D. (2007). Context-dependent phrasal translation lexicons for statistical machine translation. Proceedings of Machine Translation Summit XI, pages 73-80.
  7. Cer, D., Galley, M., Jurafsky, D., and Manning, C. D. (2010). Phrasal: A statistical machine translation toolkit for exploring new model. Proceedings of the NAACL HLT 2010 Demon- stration Session, pages 9-12.
  8. Chahuneau, V., Schlinger, E., Smith, N. A., and Dyer, C. (2013). Translating into morpho- logically rich languages with synthetic phrases. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1677-1687, Seattle, Washington, USA. Association for Computational Linguistics.
  9. Collins, M., Koehn, P., and Kucerova, I. (2005). Clause restructuring for statistical machine translation. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05), pages 531-540, Ann Arbor, Michigan. Association for Computational Linguistics.
  10. Denkowski, M. and Lavie, A. (2011). Meteor 1.3: Automatic metric for reliable optimization and evaluation of machine translation systems. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages 85-91, Edinburgh, Scotland. Association for Compu- tational Linguistics.
  11. Fraser, A., Weller, M., Cahill, A., and Cap, F. (2012). Modeling inflection and word-formation in SMT. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 664-674, Avignon, France. Association for Computa- tional Linguistics.
  12. Jeong, M., Toutanova, K., Suzuki, H., and Quirk, C. (2010). A discriminative lexicon model for complex morphology. In Proceedings of the Ninth Conference of the Association for Machine Translation in the Americas (AMTA 2010).
  13. Kendall, M. G. (1938). A new measure of rank correlation. Biometrika, pages 81-93.
  14. Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In Proceed- ings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 388-395. Association for Computational Linguistics.
  15. Koehn, P. (2005). Europarl: A parallel corpus for statistical machine translation. In Proceedings of Machine Translation Summit X, volume 5, pages 79-86.
  16. Lerner, U. and Petrov, S. (2013). Source-side classifier preordering for machine translation. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 513-523, Seattle, Washington, USA. Association for Computational Linguistics.
  17. Machacek, M. and Bojar, O. (2014). Results of the WMT14 metrics shared task. In Proceed- ings of the Ninth Workshop on Statistical Machine Translation, pages 293-301, Baltimore, Maryland, USA. Association for Computational Linguistics.
  18. Martins, A., Smith, N., Xing, E., Aguiar, P., and Figueiredo, M. (2010). Turbo parsers: Depen- dency parsing by approximate variational inference. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 34-44, Cambridge, MA. As- sociation for Computational Linguistics.
  19. Mueller, T., Schmid, H., and Schütze, H. (2013). Efficient higher-order CRFs for morphological tagging. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 322-332, Seattle, Washington, USA. Association for Computational Lin- guistics.
  20. Nivre, J. and Nilsson, J. (2005). Pseudo-projective dependency parsing. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05), pages 99-106, Ann Arbor, Michigan. Association for Computational Linguistics.
  21. Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2002). BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311-318. Association for Computational Linguistics.
  22. Petrov, S., Barrett, L., Thibaux, R., and Klein, D. (2006). Learning accurate, compact, and in- terpretable tree annotation. In Proceedings of the 21st International Conference on Computa- tional Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 433-440, Sydney, Australia. Association for Computational Linguistics.
  23. Quirk, C., Menezes, A., and Cherry, C. (2005). Dependency treelet translation: Syntactically informed phrasal SMT. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05), pages 271-279, Ann Arbor, Michigan. Association for Computational Linguistics.
  24. Toutanova, K., Suzuki, H., and Ruopp, A. (2008). Applying morphology generation models to machine translation. In Proceedings of ACL-08: HLT, pages 514-522, Columbus, Ohio. Association for Computational Linguistics.
  25. Tran, K., Bisazza, A., and Monz, C. (2014). Word translation prediction for morphologically rich languages with bilingual neural networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Association for Computational Lin- guistics.
  26. Williams, P. and Koehn, P. (2011). Agreement constraints for statistical machine translation into German. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages 217-226, Edinburgh, Scotland. Association for Computational Linguistics.
  27. Yeniterzi, R. and Oflazer, K. (2010). Syntax-to-morphology mapping in factored phrase-based statistical machine translation from English to Turkish. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 454-464, Uppsala, Sweden. Association for Computational Linguistics.
  28. Zeman, D. (2008). Reusable tagset conversion using tagset drivers. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08).
  29. Zeman, D., Mareček, D., Popel, M., Ramasamy, L., Štěpánek, J., Žabokrtský, Z., and Hajič, J. (2012). Hamledt: To parse or not to parse? In Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12), Istanbul, Turkey. European Language Resources Association (ELRA).

Related papers

Generating complex morphology for machine translation
Einat Minkov

2007

We present a novel method for predicting inflected word forms for generating morphologically rich languages in machine translation. We utilize a rich set of syntactic and morphological knowledge sources from both source and target sentences in a probabilistic model, and evaluate their contribution in generating Russian and Arabic sentences. Our results show that the proposed model substantially outperforms the commonly used baseline of a trigram target language model; in particular, the use of morphological and syntactic features leads to large gains in prediction accuracy. We also show that the proposed method is effective with a relatively small amount of data.

View PDFchevron_right
Integration of Morphology into Statistical Machine Translation
Stephan Vogel

2008

The state-of-the-art in machine translation (MT) is statistical machine translation (SMT). Such models began as word-based models, but they have evolved to phrase-based models, as translating chunks of the input text at a time yields better results than merely translating word-by-word. Phrase-based SMT systems assume that it is possible to construct a target sentence by segmenting a source sentence into phrases, translating each phrase, and combining the translated phrases to create the target sentence.

View PDFchevron_right
A hybrid morpheme-word representation for machine translation of morphologically rich languages
Min-Yen Kan

2010

Abstract We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process.

View PDFchevron_right
Morphologically Aware Word-Level Translation
Paula Czarnowska

Proceedings of the 28th International Conference on Computational Linguistics, 2020

We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning, while inflectional morphology provides additional syntactic information. This approach leads to substantial performance improvements-19% average improvement in accuracy across 6 language pairs over the state of the art in the supervised setting and 16% in the weakly supervised setting. As another contribution, we highlight issues associated with modern BLI that stem from ignoring inflectional morphology, and propose three suggestions for improving the task.

View PDFchevron_right
Addressing SMT Data Sparseness when Translating into Morphologically-Rich Languages
Dan Tufis

2011

The phrase-based translation approach has overcome several drawbacks of the word-based translation methods and proved to significantly improve the quality of translated output. However, they show less improvement on translating between languages with very different syntax and morphology, especially when the translation direction is from a language with limited word order and morphological variations to a highly inflected language. We describe an experiment that uses morpho-syntactic descriptions to translate and generate morphological information in factored machine translation. We show that from English to a morphologically rich language this setting has better performance than the baseline phrase-based system, when only a small parallel corpus is available. Also, we show that it scales well to a large parallel corpus when additional target monolingual corpus is available.

View PDFchevron_right

Related topics

  • Computer Science
  • Artificial Intelligence
  • Natural Language Processing
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved