no code implementations • EMNLP (BlackboxNLP) 2021 • Adly Templeton
Therefore, each dimension of our sparse vectors corresponds to a natural language word.
no code implementations • 8 Apr 2020 • Adly Templeton
We also show that models trained using these sparse embeddings can achieve good performance and are more interpretable in practice, including through human evaluations.
no code implementations • 16 Oct 2018 • Adly Templeton, Jugal Kalita
To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties.
no code implementations • ICLR 2018 • Adly Templeton, Jugal Kalita
Vector semantics, especially sentence vectors, have recently been used successfully in many areas of natural language processing.