Computing Semantic Text Similarity Using Rich Features

Semantic text similarity (STS) is an essential problem in many Natural Language Processing tasks, which has drawn a considerable amount of attention by research community in recent years. In this paper, our work focused on computing semantic similarity between texts of sentence length. We employed a Support Vector Regression model with rich effective features to predict the similarity scores between short English sentence pairs. Our model used WordNet-Based features, CorpusBased features, Word2Vec-based features, Alignment-Based feature and Literal-Based features to cover various aspects of sentences. And the experiment conducted on SemEval 2015 task 2a shows that our method achieved a Pearson correlation: 80.486% which outperformed the wining system (80.15%) by a small margin, the results indicated a high correlation with human judgments. Specially, among the five test sets which come from different domains used in the estimation, our method got better results than the top team on two of them whose domain-related data is available for training, while comparable results were achieved on the rest three unseen test sets. The experiments results indicated that our solution is more competitive when the domain-specific training data is available and our method still keeps good generalization ability on novel data.