UdL at SemEval-2017 Task 1: Semantic Textual Similarity Estimation of English Sentence Pairs Using Regression Model over Pairwise Features
This paper describes the model UdL we proposed to solve the semantic textual similarity task of SemEval 2017 workshop. The track we participated in was estimating the semantics relatedness of a given set of sentence pairs in English. The best run out of three submitted runs of our model achieved a Pearson correlation score of 0.8004 compared to a hidden human annotation of 250 pairs. We used random forest ensemble learning to map an expandable set of extracted pairwise features into a semantic similarity estimated value bounded between 0 and 5. Most of these features were calculated using word embedding vectors similarity to align Part of Speech (PoS) and Name Entities (NE) tagged tokens of each sentence pair. Among other pairwise features, we experimented a classical tf-idf weighted Bag of Words (BoW) vector model but with character-based range of n-grams instead of words. This sentence vector BoW-based feature gave a relatively high importance value percentage in the feature importances analysis of the ensemble learning.
PDF Abstract
