@inproceedings{a7b3629f957f4ff99e91e1362181bc52,
title = "Sentence embedding evaluation using pyramid annotation",
abstract = "Word embedding vectors are used as input for a variety of tasks. Choosing the right model and features for producing such vectors is not a trivial task and different embedding methods can greatly affect results. In this paper we repurpose the {"}Pyramid Method{"} annotations used for evaluating automatic summarization to create a benchmark for comparing embedding models when identifying paraphrases of text snippets containing a single clause. We present a method of converting pyramid annotation files into two distinct sentence embedding tests. We show that our method can produce a good amount of testing data, analyze the quality of the testing data, perform test on several leading embedding methods, and finally explain the downstream usages of our task and its significance.",
author = "Tal Baumel and Raphael Cohen and Michael Elhadad",
note = "Publisher Copyright: {\textcopyright} 2016 Proceedings of the Annual Meeting of the Association for Computational Linguistics. All Rights Reserved.; 1st Workshop on Evaluating Vector-Space Representations for NLP, RepEval 2016 at the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 ; Conference date: 07-08-2016",
year = "2016",
month = jan,
day = "1",
doi = "https://doi.org/10.18653/v1/W16-2526",
language = "American English",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "145--149",
booktitle = "Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, RepEval 2016 at the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016",
address = "United States",
}