Skip to main content
Presentation
CECL: a new baseline and a non-compositional approach for the Sick benchmark.
Proceedings of SemEval 2014 : The 8th International Workshop on Semantic Evaluation (pp. 160-165). Association for Computational Linguistics. (2014)
  • Yves Bestgen, Université catholique de Louvain
Abstract
This paper describes the two procedures for determining the semantic similarities between sentences submitted for the SemEval 2014 Task 1. MeanMaxSim, an unsupervised procedure, is proposed as a new baseline to assess the efficiency gain provided by compositional models. It outperforms a number of other baselines by a wide margin. Compared to the word-overlap baseline, it has the advantage of taking into account the distributional similarity between words that are also involved in compositional models. The second procedure aims at building a predictive model using as predictors MeanMaxSim and (transformed) lexical features describing the differences between each sentence of a pair. It finished sixth out of 17 teams in the textual similarity sub-task and sixth out of 19 in the textual entailment subtask.
Publication Date
2014
Citation Information
Yves Bestgen. "CECL: a new baseline and a non-compositional approach for the Sick benchmark." Proceedings of SemEval 2014 : The 8th International Workshop on Semantic Evaluation (pp. 160-165). Association for Computational Linguistics. (2014)
Available at: http://works.bepress.com/yvesbestgen/6/