5 citations · 6 across the 4 of their papers we have counts for
4 papers
Learning to Ask Like a Physician
Eric Lehman, Vladislav Lialin, Katelyn Y. Legaspi +15
Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and consequently fail to capture realistic physician information n…
Life after BERT: What do Other Muppets Understand about Language?
Vladislav Lialin, Kevin Zhao, Namrata Shivagunde +1
Existing pre-trained transformer analysis works usually focus only on one or two model families at a time, overlooking the variability of the architecture and pre-training objectiv…
Update Frequently, Update Fast: Retraining Semantic Parsing Systems in a Fraction of Time
Vladislav Lialin, Rahul Goel, Andrey Simanovsky +2
Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. E…
Injecting Hierarchy with U-Net Transformers
David Donahue, Vladislav Lialin, Anna Rumshisky
The Transformer architecture has become increasingly popular over the past two years, owing to its impressive performance on a number of natural language processing (NLP) tasks. Ho…