Unsupervised quality estimation for neural machine translation
| Autor: | Frédéric Blain, Nikolaos Aletras, Francisco Guzmán, Lisa Yankovskaya, Mark Fishel, Lucia Specia, Marina Fomicheva, Shuo Sun, Vishrav Chaudhary |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Linguistics and Language Machine translation Computer science Computation media_common.quotation_subject 1702 Cognitive Sciences 02 engineering and technology 010501 environmental sciences Translation (geometry) computer.software_genre Machine learning 2004 Linguistics 01 natural sciences Artificial Intelligence Black box Component (UML) 0202 electrical engineering electronic engineering information engineering 0801 Artificial Intelligence and Image Processing Quality (business) Uncertainty quantification 0105 earth and related environmental sciences media_common Estimation Computer Science - Computation and Language business.industry Communication Computer Science Applications Human-Computer Interaction 020201 artificial intelligence & image processing Artificial intelligence business computer Computation and Language (cs.CL) |
| ISSN: | 2307-387X |
| Popis: | Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time. Existing approaches require large amounts of expert annotated data, computation and time for training. As an alternative, we devise an unsupervised approach to QE where no training or access to additional resources besides the MT system itself is required. Different from most of the current work that treats the MT system as a black box, we explore useful information that can be extracted from the MT system as a by-product of translation. By employing methods for uncertainty quantification, we achieve very good correlation with human judgments of quality, rivalling state-of-the-art supervised QE models. To evaluate our approach we collect the first dataset that enables work on both black-box and glass-box approaches to QE. Comment: Accepted for publication in TACL. Authors' final version |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|