UMBC ebiquity
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
Ebiquity: Paraphrase and Semantic Similarity in Twitter using Skipgram
June 4, 2015
We describe the system we developed to participate in SemEval 2015 Task 1, Paraphrase and Semantic Similarity in Twitter. We create similarity vectors from two-skip trigrams of preprocessed tweets and measure their semantic similarity using our UMBC-STS system. We submitted two runs. The best result is ranked eleventh out of eighteen teams with F1 score of 0.599. In this task, participants were given pairs of text sequences from Twitter trends and produced a binary judgment for each, indicating whether they were paraphrases (i.e., semantically equivalent), and optionally a graded score (0.0 to 1.0) measuring their degree of semantic equivalence.
InProceedings
Association for Computational Linguistics
DOI: 10.18653/v1/S15-2009
Downloads: 1464 downloads