Machine Translation Evaluation with BERT Regressor

07/29/2019
by   Hiroki Shimanaka, et al.
0

We introduce the metric using BERT (Bidirectional Encoder Representations from Transformers) (Devlin et al., 2019) for automatic machine translation evaluation. The experimental results of the WMT-2017 Metrics Shared Task dataset show that our metric achieves state-of-the-art performance in segment-level metrics task for all to-English language pairs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/18/2018

Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations

Sentence representations can capture a wide range of information that ca...
research
10/08/2020

Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task

The quality of machine translation systems has dramatically improved ove...
research
03/29/2022

Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics

Current practices in metric evaluation focus on one single dataset, e.g....
research
11/24/2020

Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning

The Winograd Schema Challenge (WSC) is a common-sense reasoning task tha...
research
11/02/2019

Machine Translation Evaluation using Bi-directional Entailment

In this paper, we propose a new metric for Machine Translation (MT) eval...
research
07/25/2018

"Bilingual Expert" Can Find Translation Errors

Recent advances in statistical machine translation via the adoption of n...
research
05/16/2019

Latent Universal Task-Specific BERT

This paper describes a language representation model which combines the ...

Please sign up or login with your details

Forgot password? Click here to reset