WMT 2019

此共享任务将检查机器翻译的自动评估指标。共享指标任务的目标是： 实现与人类对翻译质量的判断的最强相关性；说明自动评估指标作为人工评估替代指标的适用性；解决与单一参考翻译比较相关的问题；将自动评估从系统级排序转移到更细粒度的句子级排序。此任务的所有数据集都可在此处获得。

This shared task examines automatic evaluation metrics for machine translation. The goals of the shared metrics task are: to achieve the strongest correlation with human judgments of translation quality; to demonstrate the applicability of automatic evaluation metrics as a surrogate for human evaluation; to address issues related to comparison against a single reference translation; and to shift automatic evaluation from system-level ranking to more fine-grained sentence-level ranking. All datasets for this task are available here.

搜集汇总

背景与挑战

背景概述

WMT 2019是一个专注于机器翻译自动评估指标的数据集，旨在通过共享任务提升指标与人类判断的相关性，并推动评估从系统级向更细粒度的句子级发展。该数据集由多所大学和企业于2019年联合发布，适用于自然语言处理中的机器翻译研究和评估。