This paper is concerned withthe problem of paraphrase detection. For a number of applications, the ability to detect similar sentences, such as text mining, summary text, plagiarism detection, authorship authentication, and question answering, is important. Given two phrases, the goal is to detect whether they are identical semantically. This work involves a novel model namely, ParaCap, which uses capsule networks for the investigation of sentences. Capsule networks understand the spatial information (context, language, length of sentences and others) by using the instantiation parameters for the better results as compared to CNNs. For the objective, the Quora Question Pair dataset containing 404291 pairs of Quora Questions is being used. The ParaCap model outperforms many state-of-art methods, and also proves to be comparable to other techniques by achieving the accuracy of 89.19%.

本文涉及释义检测的问题。对于许多应用程序来说，检测类似句子的能力非常重要，例如文本挖掘，摘要文本，抄袭检测，作者身份验证和问题回答。给定两个短语，目标是检测它们在语义上是否相同。这项工作涉及一种新颖的模型ParaCap，该模型使用胶囊网络进行句子调查。与CNN相比，胶囊网络通过使用实例化参数了解空间信息（上下文，语言，句子的长度等），以获得更好的结果。为了达到目标，正在使用包含404291对Quora问题对的Quora问题对数据集。ParaCap模型优于许多最新方法，