Text Similarity Identification Based on CNN and CNN-LSTM Model

Abstract

AbstractNatural Language Processing is an active area of research where new challenges and issues such as text similarity, semantic analysis, paraphrase identification, citation matching, and language translation, etc. foster the need to further exploit this area. Among the above issues, text similarity is one of the key operative challenges which is being explored by many researchers. In text similarity, extracting the meaningful word, phrase, and sentence patterns from texts requires an effective way that can be evaluated based on various standardized metrics. Therefore, we propose a model based on Convolutional Neural Networks (CNN) and Convolutional Neural Networks- Long Short Term Memory (CNN-LSTM) to find the text similarity as image recognition. Our results show that we achieved better classification results with the precision of 61.3% and recall of 57.9% with MatchGridTower as compared to the earlier MatchPyramid model having a precision of 54.0% and recall of 53.1%.KeywordsConvolution neural networkLong short term memoryMachine learningNatural language processingText matchingText similarity