TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Word Similarity	WS353	Context-to-Vector	Spearman's Rho	78.9	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/using-context-to-vector-with-graph-1/word-similarity-on-ws353)](https://paperswithcode.com/sota/word-similarity-on-ws353?p=using-context-to-vector-with-graph-1)`

Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings

ACL 2022 · Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang, Stan Z. Li ·

Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due to their low computational cost, ease of deployment, and stability. In this paper, we aim to improve word embeddings by 1) incorporating more contextual information from existing pre-trained models into the Skip-gram framework, which we call Context-to-Vec; 2) proposing a post-processing retrofitting method for static embeddings independent of training by employing priori synonym knowledge and weighted vector distribution. Through extrinsic and intrinsic tasks, our methods are well proven to outperform the baselines by a large margin.