SSMT:A Machine Translation Evaluation View To Paragraph-to-Sentence Semantic Similarity
Pingping Huang, Baobao Chang · 2014
This paper presents the system SSMT measuring the semantic similarity between a paragraph and a sentence submitted to the SemEval 2014 task3: Cross-level Se-mantic Similarity. The special difficulty of this task is the length disparity between the two semantic comparison texts. We adapt several machine translation evalua-tion 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. 1