no code implementations • ICLR 2018 • Eric Bailey, Charles Meyer, Shuchin Aeron
We present two new word embedding techniques based on tensor factorization and show that they outperform common methods on several semantic NLP tasks when given the same data.
1 code implementation • 10 Apr 2017 • Eric Bailey, Shuchin Aeron
We show that embeddings based on tensor factorization can be used to discern the various meanings of polysemous words without being explicitly trained to do so, and motivate the intuition behind why this works in a way that doesn't with existing methods.