no code implementations • Findings (EMNLP) 2021 • Sameer Khanna
By noting that the range of documents we wish to identify can be represented as positive linear combinations of the Vector Space Model representing our text, we propose Conical classification, an approach that allows us to identify if a document is of a particular topic in a computationally efficient manner.
no code implementations • 9 Aug 2023 • Sameer Khanna, Adam Dejl, Kibo Yoon, Quoc Hung Truong, Hanh Duong, Agustina Saenz, Pranav Rajpurkar
We present RadGraph2, a novel dataset for extracting information from radiology reports that focuses on capturing changes in disease state and device placement over time.
1 code implementation • 25 Nov 2021 • Sameer Khanna
Insider threats are costly, hard to detect, and unfortunately rising in occurrence.
no code implementations • 31 Oct 2021 • Sameer Khanna
By noting that the range of documents we wish to identify can be represented as positive linear combinations of the Vector Space Model representing our text, we propose Conical classification, an approach that allows us to identify if a document is of a particular topic in a computationally efficient manner.