Search Results for author:
Found 4 papers, 0 papers with code
Word Equations: Inherently Interpretable Sparse Word Embeddings through Sparse Coding
Therefore, each dimension of our sparse vectors corresponds to a natural language word.
Word Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding
We also show that models trained using these sparse embeddings can achieve good performance and are more interpretable in practice, including through human evaluations.
Exploring Sentence Vector Spaces through Automatic Summarization
To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties.
Exploring Sentence Vectors Through Automatic Summarization
Vector semantics, especially sentence vectors, have recently been used successfully in many areas of natural language processing.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
