ECNUCS: Measuring Short Text Semantic Equivalence Using Multiple Similarity Measurements

This paper reports our submissions to the Semantic Textual Similarity (STS) task in ∗SEM Shared Task 2013. We submitted three Support Vector Regression (SVR) systems in core task, using 6 types of similarity measures, i.e., string similarity, number similarity, knowledge-based similarity, corpus-based similarity, syntactic dependency similarity and machine translation similarity. Our third system with different training data and different feature sets for each test data set performs the best and ranks 35 out of 90 runs. We also submitted two systems in typed task using string based measure and Named Entity based measure. Our best system ranks 5 out of 15 runs.