Search Results for author:
Found 2 papers, 1 papers with code
Towards Generating Informative Textual Description for Neurons in Language Models
We leverage the potential of generative language models to discover human-interpretable descriptors present in a dataset and use an unsupervised approach to explain neurons with these descriptors.
Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information
Specifically, we suggest employing Bayesian inference to incorporate the sense definitions when sense information of the answer is not provided.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
