DeepAI
Log In Sign Up

Exploring Distantly-Labeled Rationales in Neural Network Models

06/03/2021
by   Quzhe Huang, et al.
0

Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existing methods distribute their models' focus to distantly-labeled rationale words entirely and equally, while ignoring the potential important non-rationale words and not distinguishing the importance of different rationale words. In this paper, we propose two novel auxiliary loss functions to make better use of distantly-labeled rationales, which encourage models to maintain their focus on important words beyond labeled rationales (PINs) and alleviate redundant training on non-helpful rationales (NoIRs). Experiments on two representative classification tasks show that our proposed methods can push a classification model to effectively learn crucial clues from non-perfect rationales while maintaining the ability to spread its focus to other unlabeled important words, thus significantly outperform existing methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/18/2020

Text Classification with Lexicon from PreAttention Mechanism

A comprehensive and high-quality lexicon plays a crucial role in traditi...
12/31/2021

Domain Adaptation with Category Attention Network for Deep Sentiment Analysis

Domain adaptation tasks such as cross-domain sentiment classification ai...
10/14/2020

Text Classification Using Label Names Only: A Language Model Self-Training Approach

Current text classification methods typically require a good number of h...
09/09/2021

EvilModel 2.0: Hiding Malware Inside of Neural Network Models

While artificial intelligence (AI) is widely applied in various areas, i...
02/03/2022

Certifying Out-of-Domain Generalization for Blackbox Functions

Certifying the robustness of model performance under bounded data distri...
02/02/2018

Complex Network Classification with Convolutional Neural Network

Classifying large scale networks into several categories and distinguish...