Style-Transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric
Abstract
The rapid development of such natural language processing tasks as style transfer, paraphrase, and machine translation often calls for the use of semantic similarity metrics. In recent years a lot of methods to measure the semantic similarity of two short texts were developed. This paper provides a comprehensive analysis for more than a dozen of such methods. Using a new dataset of fourteen thousand sentence pairs human-labeled according to their semantic similarity, we demonstrate that none of the metrics widely used in the literature is close enough to human judgment in these tasks. A number of recently proposed metrics provide comparable results, yet Word Mover Distance is shown to be the most reasonable solution to measure semantic similarity in reformulated texts at the moment.
Cite
Text
Yamshchikov et al. "Style-Transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I16.17672Markdown
[Yamshchikov et al. "Style-Transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/yamshchikov2021aaai-style/) doi:10.1609/AAAI.V35I16.17672BibTeX
@inproceedings{yamshchikov2021aaai-style,
title = {{Style-Transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric}},
author = {Yamshchikov, Ivan P. and Shibaev, Viacheslav and Khlebnikov, Nikolay and Tikhonov, Alexey},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {14213-14220},
doi = {10.1609/AAAI.V35I16.17672},
url = {https://mlanthology.org/aaai/2021/yamshchikov2021aaai-style/}
}