We address the problem of automatically cleaning a large-scale Translation Memory (TM) in a fully unsupervised fashion, i.e. without human-labelled data. We approach the task by: i) designing a set of features that capture the similarity between two text segments in different languages, ii) use them to induce reliable training labels for a subset of the translation units (TUs) contained in the TM, and iii) use the automatically labelled data to train an ensemble of binary classifiers. We apply our method to clean a test set composed of 1,000 TUs randomly extracted from the English-Italian version of MyMemory, the world’s largest public TM. Our results show competitive performance not only against a strong baseline that exploits machine translation, but also against a state-of-the-art method that relies on human-labelled data.

An Unsupervised Method for Automatic Translation Memory Cleaning.

Negri, Matteo;Turchi, Marco;
2016-01-01

Abstract

We address the problem of automatically cleaning a large-scale Translation Memory (TM) in a fully unsupervised fashion, i.e. without human-labelled data. We approach the task by: i) designing a set of features that capture the similarity between two text segments in different languages, ii) use them to induce reliable training labels for a subset of the translation units (TUs) contained in the TM, and iii) use the automatically labelled data to train an ensemble of binary classifiers. We apply our method to clean a test set composed of 1,000 TUs randomly extracted from the English-Italian version of MyMemory, the world’s largest public TM. Our results show competitive performance not only against a strong baseline that exploits machine translation, but also against a state-of-the-art method that relies on human-labelled data.
2016
978-1-945626-01-2
File in questo prodotto:
File Dimensione Formato  
P16-2047.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 130.92 kB
Formato Adobe PDF
130.92 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/307274
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact