Evaluating Embeddings for One-Shot Classification of Doctor-AI Consultations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ojo, Olumide Ebenezer, Adebanji, Olaronke Oluwayemisi, Gelbukh, Alexander, Calvo, Hiram, Feldman, Anna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914669898235904
author Ojo, Olumide Ebenezer
Adebanji, Olaronke Oluwayemisi
Gelbukh, Alexander
Calvo, Hiram
Feldman, Anna
author_facet Ojo, Olumide Ebenezer
Adebanji, Olaronke Oluwayemisi
Gelbukh, Alexander
Calvo, Hiram
Feldman, Anna
contents Effective communication between healthcare providers and patients is crucial to providing high-quality patient care. In this work, we investigate how Doctor-written and AI-generated texts in healthcare consultations can be classified using state-of-the-art embeddings and one-shot classification systems. By analyzing embeddings such as bag-of-words, character n-grams, Word2Vec, GloVe, fastText, and GPT2 embeddings, we examine how well our one-shot classification systems capture semantic information within medical consultations. Results show that the embeddings are capable of capturing semantic features from text in a reliable and adaptable manner. Overall, Word2Vec, GloVe and Character n-grams embeddings performed well, indicating their suitability for modeling targeted to this task. GPT2 embedding also shows notable performance, indicating its suitability for models tailored to this task as well. Our machine learning architectures significantly improved the quality of health conversations when training data are scarce, improving communication between patients and healthcare providers.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04442
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Embeddings for One-Shot Classification of Doctor-AI Consultations
Ojo, Olumide Ebenezer
Adebanji, Olaronke Oluwayemisi
Gelbukh, Alexander
Calvo, Hiram
Feldman, Anna
Computation and Language
Effective communication between healthcare providers and patients is crucial to providing high-quality patient care. In this work, we investigate how Doctor-written and AI-generated texts in healthcare consultations can be classified using state-of-the-art embeddings and one-shot classification systems. By analyzing embeddings such as bag-of-words, character n-grams, Word2Vec, GloVe, fastText, and GPT2 embeddings, we examine how well our one-shot classification systems capture semantic information within medical consultations. Results show that the embeddings are capable of capturing semantic features from text in a reliable and adaptable manner. Overall, Word2Vec, GloVe and Character n-grams embeddings performed well, indicating their suitability for modeling targeted to this task. GPT2 embedding also shows notable performance, indicating its suitability for models tailored to this task as well. Our machine learning architectures significantly improved the quality of health conversations when training data are scarce, improving communication between patients and healthcare providers.
title Evaluating Embeddings for One-Shot Classification of Doctor-AI Consultations
topic Computation and Language
url https://arxiv.org/abs/2402.04442