Reranking Bilingually Extracted Paraphrases Using Monolingual Distributional Similarity
Reranking Bilingually Extracted Paraphrases Using Monolingual Distributional Similarity
复制标题
使用单语分布相似性对双语提取的释义进行重新排序
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Benjamin Van Durme
中科院分区：
文献类型：
--
作者：
Tsz Ping Chan;Chris Callison;Benjamin Van Durme
本文使用与Rerank候选释义的单语分布相似性改善了现有的双语释义技术。原始单语数据提供了一种互补和正交的信息来源，可减少基于双语枢轴方法中通常观察到的错误。我们的实验表明，双语提取的释义的单语评分与人类对语法的判断的相关性明显与双语枢纽方法所分配的概率相关。结果还表明，单语分布相似性可以作为高精度释义选择的阈值。
This paper improves an existing bilingual paraphrase extraction technique using monolingual distributional similarity to rerank candidate paraphrases. Raw monolingual data provides a complementary and orthogonal source of information that lessens the commonly observed errors in bilingual pivot-based methods. Our experiments reveal that monolingual scoring of bilingually extracted paraphrases has a significantly stronger correlation with human judgment for grammaticality than the probabilities assigned by the bilingual pivoting method does. The results also show that monolingual distribution similarity can serve as a threshold for high precision paraphrase selection.