no code implementations • 6 Jun 2023 • Maksim Eremeev, Ilya Valmianski, Xavier Amatriain, Anitha Kannan
For high-stake domains that are also knowledge-rich, we show how to use knowledge to (a) identify which rare tokens that appear in both source and reference are important and (b) uplift their conditional probability.
no code implementations • 4 Apr 2023 • Jian Zhu, Ilya Valmianski, Anitha Kannan
We find that relative to the expert system, the best performance is achieved by our proposed global re-ranker with a transformer backbone, resulting in a 30% higher normalized discount cumulative gain (nDCG) and a 77% higher mean average precision (mAP).
1 code implementation • 6 Oct 2022 • Mengqian Wang, Ilya Valmianski, Xavier Amatriain, Anitha Kannan
This paper presents an approach that tackles the problem of learning to classify medical dialogue into functional sections without requiring a large number of annotations.
1 code implementation • 12 Jul 2022 • Raymond Li, Ilya Valmianski, Li Deng, Xavier Amatriain, Anitha Kannan
In this paper, we propose a method for linking an open set of entities that does not require any span annotations.
1 code implementation • 17 Nov 2021 • Rhys Compton, Ilya Valmianski, Li Deng, Costa Huang, Namit Katariya, Xavier Amatriain, Anitha Kannan
We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controllable Dialog system with a unique approach to the natural language generator module.
1 code implementation • 15 Nov 2021 • Varun Nair, Namit Katariya, Xavier Amatriain, Ilya Valmianski, Anitha Kannan
Summarized conversations are used to facilitate patient hand-offs between physicians, and as part of providing care in the future.
no code implementations • 19 Oct 2020 • Ilya Valmianski, Nave Frost, Navdeep Sood, Yang Wang, Baodong Liu, James J. Zhu, Sunil Karumuri, Ian M. Finn, Daniel S. Zisook
Symptom checkers have emerged as an important tool for collecting symptoms and diagnosing patients, minimizing the involvement of clinical personnel.
no code implementations • 15 Nov 2019 • Ilya Valmianski, Caleb Goodwin, Ian M. Finn, Naqi Khan, Daniel S. Zisook
In this work, we evaluate several approaches to chief complaint classification using a novel Chief Complaint (CC) Dataset that contains ~200, 000 patient-generated reasons-for-visit entries mapped to a set of 795 discrete chief complaints.