We explore using recursive autoencoders for SemEval 2015 Task 1: Paraphrase and Semantic Similarity in Twitter. Our paraphrase detection system makes use of phrase-structure parse tree embeddings that are then provided as input to a conventional supervised classification model. We achieve an F1 score of 0.45 on paraphrase identification and a Pearson correlation of 0.303 on computing semantic similarity.
P. Soman Kotti, Mahalakshmi, S. Sundaram, and Kumar, M. Anand, “AMRITA CEN@ SemEval-2015: Paraphrase Detection for Twitter using Unsupervised Feature Learning with Recursive Autoencoders”, Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval). 2015. ACL, Denver, Colorado, pp. 45-50, 2015.