TransQuest: Translation Quality Estimation with Cross-lingual Transformers

by   Tharindu Ranasinghe, et al.

Recent years have seen big advances in the field of sentence-level quality estimation (QE), largely as a result of using neural-based architectures. However, the majority of these methods work only on the language pair they are trained on and need retraining for new language pairs. This process can prove difficult from a technical point of view and is usually computationally expensive. In this paper we propose a simple QE framework based on cross-lingual transformers, and we use it to implement and evaluate two different neural architectures. Our evaluation shows that the proposed methods achieve state-of-the-art results outperforming current open-source quality estimation frameworks when trained on datasets from WMT. In addition, the framework proves very useful in transfer learning settings, especially when dealing with low-resourced languages, allowing us to obtain very competitive results.


TransQuest at WMT2020: Sentence-Level Direct Assessment

This paper presents the team TransQuest's participation in Sentence-Leve...

An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers

Most studies on word-level Quality Estimation (QE) of machine translatio...

Trans-gram, Fast Cross-lingual Word-embeddings

We introduce Trans-gram, a simple and computationally-efficient method t...

Massively Multilingual Document Alignment with Cross-lingual Sentence-Mover's Distance

Cross-lingual document alignment aims to identify pairs of documents in ...

Scalable Cross-Lingual Transfer of Neural Sentence Embeddings

We develop and investigate several cross-lingual alignment approaches fo...

A Neighbourhood Framework for Resource-Lean Content Flagging

We propose a novel interpretable framework for cross-lingual content fla...