-
Unsupervised alignment of embeddings with Wasserstein procrustes
This study introduces a new method for unsupervised alignment of embeddings with Wasserstein procrustes. -
Discovering Universal Geometry in Embeddings with ICA
This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. -
PubMed abstracts
The dataset used in this paper is the PubMed abstracts dataset, which contains approximately 11 million abstracts. -
Retroļ¬tting word vectors to semantic lexicons
PPDB is a paraphrase database used for training word embeddings. -
Word2Vec: A Novel Semi-Supervised Learning Approach for Word Embeddings
Word2Vec is a technique for learning vector representations of words in a text corpus. -
SemEval datasets
The dataset used in the paper is the SemEval-2, SemEval-3, SemEval'07, SemEval'13, and SemEval'15 datasets, which contain manually annotated word sense groups. -
SemCor dataset
The dataset used in the paper is the SemCor dataset, which contains manually annotated word sense groups.
