ATEC: automatic evaluation of machine translation via word choice and word order
ATEC: automatic evaluation of machine translation via word choice and word order
复制标题
DOI：
10.1007/s10590-009-9061-x
复制
发表时间：
2009-09
影响因子：
1.9
通讯作者：
B. Wong;Chunyu Kit
中科院分区：
文献类型：
--
作者：
B. Wong;Chunyu Kit
我们提出了一种新的度量ATEC自动MT评估的基础上明确评估的词的选择和词序在MT输出相比，其参考翻译（S），两个最基本的因素，在建设的意义为一个句子。前者是通过匹配不同语言层次的词形来评估的，包括表面形式，词干，声音和意义，并进一步衡量每个词的信息量。后者是量化的词的位置和词的顺序之间的候选翻译和参考的不一致。在使用MetricsMATR08数据集和LDC MTC2和MTC4语料库进行的评估中，ATEC在细分层面上与人类判断呈现出令人印象深刻的正相关性，与少数最先进的评估指标高度可比。
We propose a novel metric ATEC for automatic MT evaluation based on explicit assessment of word choice and word order in an MT output in comparison to its reference translation(s), the two most fundamental factors in the construction of meaning for a sentence. The former is assessed by matching word forms at various linguistic levels, including surface form, stem, sound and sense, and further by weighing the informativeness of each word. The latter is quantified in term of the discordance of word position and word sequence between a translation candidate and its reference. In the evaluations using the MetricsMATR08 data set and the LDC MTC2 and MTC4 corpora, ATEC demonstrates an impressive positive correlation to human judgments at the segment level, highly comparable to the few state-of-the-art evaluation metrics.