Word Embeddings at Post-Editing

Author(s)

Inacio, Marcio Lima ; Caseli, Helena de Medeiros ; Quaresma, P ; Vieira, R ; Aluisio, S ; Moniz, H ; Batista, F ; Goncalves, T

• Document type: Journal article
• Source: COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE, PROPOR 2020; v. 12037, p. 12-pg., 2020-01-01.

Abstract

After more than 60 years of research in Machine Translation, it has not been possible yet to develop a perfect fully automatic translation system for unlimited purposes. Thus, it is still necessary post-editing to correct possible mistranslations output by the Machine Translation system. Several approaches have been proposed in order to also automate the post-editing task. This work addresses one of the main steps of an automatic post-editing tool: the automatic proposition of word replacements for a Machine Translation output. To do so, we propose a novel method based on bilingual word embeddings. In the experiments present in this paper we show the effectiveness of this approach in two of the most frequent lexical errors: 'not translated word' and 'incorrectly translated word'. (AU)

• FAPESP's process: 16/21317-0 - Semantic driven automated post-editing for Brazilian Portuguese
• Grantee: Marcio Lima Inácio
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• FAPESP's process: 16/13002-0 - MMeaning - multimodal distributional semantic models
• Grantee: Helena de Medeiros Caseli
• Support Opportunities: Regular Research Grants