activity
20192022
most citedGenerating Hierarchical Explanations on Text Classification via Feature Interaction Detection

11 citations · 18 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL2022

Pathologies of Pre-trained Language Models in Few-shot Fine-tuning

Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah +1

Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance ga…

cs.CL2022

Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation

Hanjie Chen, Yangfeng Ji

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A commo…

cs.CL2021

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon +2

Interpretability methods like Integrated Gradient and LIME are popular choices for explaining natural language model predictions with relative word importance scores. These interpr…

cs.CL20212 cited

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks

Hanjie Chen, Song Feng, Jatin Ganhotra +4

Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural netwo…

cs.CL20205 cited

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers

Hanjie Chen, Yangfeng Ji

To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations. A new line of wo…

cs.CL202011 cited

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection

Hanjie Chen, Guangtao Zheng, Yangfeng Ji

Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing,…