Reference-less Measure of Faithfulness for Grammatical Error Correction.

NAACL-HLT(2018)

引用 34|浏览75
暂无评分
摘要
We propose USim, a semantic measure for Grammatical Error Correction (GEC) that measures the semantic faithfulness of the output to the source, thereby complementing existing reference-less measures (RLMs) for measuring the outputu0027s grammaticality. USim operates by comparing the semantic symbolic structure of the source and the correction, without relying on manually-curated references. Our experiments establish the validity of USim, by showing that (1) semantic annotation can be consistently applied to ungrammatical text; (2) valid corrections obtain a high USim similarity score to the source; and (3) invalid corrections obtain a lower score.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要