Multi-Task Word Alignment Triangulation for Low-Resource Languages

We present a multi-task learning approach that jointly trains three word alignment models over disjoint bitexts of three languages: source, target and pivot. Our approach builds upon model triangulation, following Wang et al., which approximates a source-target model by combining source-pivot and pivot-target models. We develop a MAP-EM algorithm that uses triangulation as a prior, and show how to extend it to a multi-task setting. On a low-resource Czech-English corpus, using French as the pivot, our multi-task learning approach more than doubles the gains in both Fand Bleu scores compared to the interpolation approach of Wang et al. Further experiments reveal that the choice of pivot language does not significantly a ect performance.

• Publication year

  2015

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  Unknown publication date

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/v1/N15-1129
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Statistical Machine Translation

  2014cited by this paper
• Pivot-based triangulation for low-resource languages

  2014cited by this paper
• Ensemble Triangulation for Statistical Machine Translation

  2013cited by this paper
• Estimating a Dirichlet distribution

  2012cited by this paper
• Improving Word Alignment with Bridge Languages

  2007cited by this paper
• Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora

  2007cited by this paper
• Word Alignment for Languages with Scarce Resources Using Bilingual Corpora of Other Language Pairs

  2006influential reference
• Leveraging multiple languages to improve statistical MT word alignments

  2005cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005influential reference
• HMM-Based Word Alignment in Statistical Translation

  1996influential reference
• 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

• Noisy Parallel Data Alignment

  2023cites this paper
• Health Care Misinformation: an Artificial Intelligence Challenge for Low-resource languages

  2020cites this paper
• Should All Cross-Lingual Embeddings Speak English?

  2019cites this paper
• Tied Multitask Learning for Neural Speech Translation

  2018cites this paper
• Linguistic-Relationships-Based Approach for Improving Word Alignment

  2017cites this paper
• Cross-lingual alignment transfer: a chicken-and-egg story?

  2016cites this paper