Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Wen, Ximing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915049319170048
author Wen, Ximing
author_facet Wen, Ximing
contents Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My dissertation focuses on developing intrinsically interpretable models when using LMs as encoders while maintaining their superior performance via prototypical networks. I initiated my research by investigating enhancements in performance for interpretable models of sarcasm detection. My proposed approach focuses on capturing sentiment incongruity to enhance accuracy while offering instance-based explanations for the classification decisions. Later, I developed a novel white-box multi-head graph attention-based prototype network designed to explain the decisions of text classification models without sacrificing the accuracy of the original black-box LMs. In addition, I am working on extending the attention-based prototype network with contrastive learning to redesign an interpretable graph neural network, aiming to enhance both the interpretability and performance of the model in document classification.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03761
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
Wen, Ximing
Computation and Language
Artificial Intelligence
Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My dissertation focuses on developing intrinsically interpretable models when using LMs as encoders while maintaining their superior performance via prototypical networks. I initiated my research by investigating enhancements in performance for interpretable models of sarcasm detection. My proposed approach focuses on capturing sentiment incongruity to enhance accuracy while offering instance-based explanations for the classification decisions. Later, I developed a novel white-box multi-head graph attention-based prototype network designed to explain the decisions of text classification models without sacrificing the accuracy of the original black-box LMs. In addition, I am working on extending the attention-based prototype network with contrastive learning to redesign an interpretable graph neural network, aiming to enhance both the interpretability and performance of the model in document classification.
title Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.03761