Search Results for author: Elliot Schumacher

Found 11 papers, 3 papers with code

Extrinsically-Focused Evaluation of Omissions in Medical Summarization

no code implementations14 Nov 2023 Elliot Schumacher, Daniel Rosenthal, Varun Nair, Luladay Price, Geoffrey Tso, Anitha Kannan

In safety-critical domains such as medicine, more rigorous evaluation is required, especially given the potential for LLMs to omit important information in the resulting summary.

Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models

no code implementations10 May 2023 Varun Nair, Elliot Schumacher, Anitha Kannan

A medical provider's summary of a patient visit serves several critical purposes, including clinical decision-making, facilitating hand-offs between providers, and as a reference for the patient.

Decision Making Dialogue Understanding

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants

no code implementations27 Apr 2023 Albert Yu Sun, Varun Nair, Elliot Schumacher, Anitha Kannan

This scenario-guided approach produces a diverse training set of rule-violating conversations, and it provides chatbot designers greater control over the classification process.

Chatbot

Improving Zero-Shot Multi-Lingual Entity Linking

no code implementations16 Apr 2021 Elliot Schumacher, James Mayfield, Mark Dredze

Entity linking -- the task of identifying references in free text to relevant knowledge base representations -- often focuses on single languages.

Entity Linking

Clinical Concept Linking with Contextualized Neural Representations

no code implementations ACL 2020 Elliot Schumacher, Andriy Mulyar, Mark Dredze

We propose an approach to concept linking that leverages recent work in contextualized neural models, such as ELMo (Peters et al. 2018), which create a token representation that integrates the surrounding context of the mention and concept name.

Entity Linking

Discriminative Candidate Generation for Medical Concept Linking

no code implementations AKBC 2019 Elliot Schumacher, Mark Dredze

Linking mentions of medical concepts in a clinical note to a concept in an ontology enables a variety of tasks that rely on understanding the content of a medical record, such as identifying patient populations and decision support.

Predicting the Relative Difficulty of Single Sentences With and Without Surrounding Context

no code implementations EMNLP 2016 Elliot Schumacher, Maxine Eskenazi, Gwen Frishkoff, Kevyn Collins-Thompson

The problem of accurately predicting relative reading difficulty across a set of sentences arises in a number of important natural language applications, such as finding and curating effective usage examples for intelligent language tutoring systems.

A Readability Analysis of Campaign Speeches from the 2016 US Presidential Campaign

no code implementations18 Mar 2016 Elliot Schumacher, Maxine Eskenazi

Readability is defined as the reading level of the speech from grade 1 to grade 12.

Cannot find the paper you are looking for? You can Submit a new open access paper.