文章基本信息

标题：Quality Estimation without Human-labeled Data
本地全文：下载
作者：Yi-Lin Tuan ; Ahmed El-Kishky ; Adithya Renduchintala 等
期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：619-625
DOI：10.18653/v1/2021.eacl-main.50
语种：English
出版社：ACL Anthology
摘要：Quality estimation aims to measure the quality of translated content without access to a reference translation. This is crucial for machine translation systems in real-world scenarios where high-quality translation is needed. While many approaches exist for quality estimation, they are based on supervised machine learning requiring costly human labelled data. As an alternative, we propose a technique that does not rely on examples from human-annotators and instead uses synthetic training data. We train off-the-shelf architectures for supervised quality estimation on our synthetic data and show that the resulting models achieve comparable performance to models trained on human-annotated data, both for sentence and word-level prediction.