BriefGPT.xyz
Nov, 2023
一种用于疗法情感分类的通用自然语言推理方法
A Generic NLI approach for Classification of Sentiment Associated with Therapies
HTML
PDF
Rajaraman Kanagasabai, Anitha Veeramani
TL;DR
通过自然语言推理（NLI）方法，采用基于句对分类的方式预测给定文本中与治疗相关的情感，并使用Transformer模型进行训练，最佳模型取得75.22%的F1分数，相较于其他团队的提交，平均分数提高了11%（中位数提高了4%）。
Abstract
This paper describes our system for addressing
smm4h 2023
Shared Task 2 on "Classification of sentiment associated with
therapies
(aspect-oriented)". In our work, we adopt an approach based on
→