Word Embeddings based on Fixed-Size Ordinally Forgetting Encoding

no code implementations • EMNLP 2017 • Joseph Sanu, MingBin Xu, Hui Jiang, Quan Liu

In this paper, we propose to learn word embeddings based on the recent fixed-size ordinally forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence into a fixed-size representation.

Language Modelling Semantic Textual Similarity +2