Extracting Paraphrases of Technical Terms from Noisy Parallel Software Corpora

Xiaoyin Wang, David Lo, Jing Jiang, Lu Zhang, Hong Mei

Abstract: In this paper, we study the problem of extracting technical paraphrases from a parallel software corpus, namely, a collection of duplicate bug reports. Paraphrase acquisition is a fundamental task in the emerging area of text mining for software engineering. Existing paraphrase extraction methods are not entirely suitable here due to the noisy nature of bug reports. We propose a number of techniques to address the noisy data problem. The empirical evaluation shows that our method significantly improves an existing method by up to 58%.