Action Word Prediction for Neural Source Code Summarization
Sakib Haque, Aakash Bansal, et al.
SANER 2021
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a distance measure between documents called Word Mover's Distance (WMD) that aligns semantically similar words, yields unprecedented KNN classification accuracy. However, WMD is expensive to compute, and it is hard to extend its use beyond a KNN classifier. In this paper, we propose the Word Mover's Embedding (WME), a novel approach to building an unsupervised document (sentence) embedding from pre-trained word embeddings. In our experiments on 9 benchmark text classification datasets and 22 textual similarity tasks, the proposed technique consistently matches or outperforms state-of-the-art techniques, with significantly higher accuracy on problems of short length.
Sakib Haque, Aakash Bansal, et al.
SANER 2021
Zhen Zhang, Yijian Xiang, et al.
NeurIPS 2019
Kai Shen, Lingfei Wu, et al.
IJCAI 2020
Michael Boratko, Harshit Padigela, et al.
EMNLP 2018