ROB: Using Semantic Meaning to Recognize Paraphrases

Paraphrase recognition is the task of identifying whether two pieces of natural language represent similar meanings. This paper describes a system participating in the shared task 1 of SemEval 2015, which is about paraphrase detection and semantic similarity in twitter. Our approach is to exploit semantically meaningful features to detect paraphrases. An existing state-of-the-art model for predicting semantic similarity is adapted to this task. A wide variety of features is used, ranging from different types of models, to lexical overlap and synset overlap. A maximum entropy classifier is then trained on these features. In addition to the detection of paraphrases, a similarity score is also predicted, using the probabilities of the classifier. To improve the results, normalization is used as preprocessing step. Our final system achieves a F1 score of 0.620 (10th out of 18 teams), and a Pearson correlation of 0.515 (6th out of 13 teams).