ECNU: Leveraging Word Embeddings to Boost Performance for Paraphrase in Twitter

This paper describes our approaches to paraphrase recognition in Twitter organized as task 1 in Semantic Evaluation 2015. Lots of approaches have been proposed to address the paraphrasing task on conventional texts ( surveyed in (Madnani and Dorr, 2010)). In this work we examined the effectiveness of various linguistic features proposed in traditional paraphrasing task on informal texts, (i.e., Twitter), for example, string based, corpus based, and syntactic features, which served as input of a classification algorithm. Besides, we also proposed novel features based on distributed word representations, which were learned using deep learning paradigms. Results on test dataset show that our proposed features improve the performance by a margin of 1.9% in terms of F1-score and our team ranks third among 10 teams with 38 systems.