SSMT: A Machine Translation Evaluation View to Paragraph-to-Sentence Semantic Similarity

摘要

This paper presents the system SSMT measuring the semantic similarity between a paragraph and a sentence submitted to the SemEval 2014 task3: Cross-level Semantic Similarity. The special difficulty of this task is the length disparity between the two semantic comparison texts. We adapt several machine translation evaluation metrics for features to cope with this difficulty, then train a regression model for the semantic similarity prediction. This system is straightforward in intuition and easy in implementation. Our best run gets 0.808 in Pearson correlation. METEOR-derived features are the most effective ones in our experiment.