Interpretability of Sentiment Based on Erasure and Generative Models
Related studies pay more and more attentions to sentiment interpretability analysis,which aims to predict the text's emotional polarity and the evidence segments that determine the emotional polarity.Based on the dataset of sentiment classification tasks,this study proposes an erasure based method for extracting evidence segments,which analysizes the logits influence of masked words on the emotional polarity.Subsequently,the model is used to extract the evidence of partial data in the public sentiment analysis dataset and the supervised data is manually fil-tered form the auto-extracted dataset.To further improve the performance of evidence extraction,this study fine-tunes the T5 sequence generative model on supervised data.This study won the third place in the Baidu 2022 Lan-guage and Intelligent Technology Competition:Sentimental Interpretable Assessment.
sentiment interpretabilityerasure-basedsequence generative model