Search Results for author:
Found 9 papers, 3 papers with code
Human-Centered Evaluation of Explanations
The NLP community are increasingly interested in providing explanations for NLP models to help people make sense of model behavior and potentially improve human interaction with models.
Learning to Ignore Adversarial Attacks
Despite the strong performance of current NLP models, they can be brittle against adversarial attacks.
Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation
Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples.
What to Learn, and How: Toward Effective Learning from Rationales
Learning from rationales seeks to augment model prediction accuracy using human-annotated rationales (i. e. subsets of input tokens) that justify their chosen labels, often in the form of intermediate or multitask supervision.
Evaluating and Characterizing Human Rationales
Two main approaches for evaluating the quality of machine-generated rationales are: 1) using human rationales as a gold standard; and 2) automated metrics based on how rationales affect model behavior.
Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification
Text simplification reduces the language complexity of professional content for accessibility purposes.
Harnessing Explanations to Bridge AI and Humans
Machine learning models are increasingly integrated into societally critical applications such as recidivism prediction and medical diagnosis, thanks to their superior predictive power.
Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation
We conduct a large-scale, systematic study to evaluate the existing evaluation methods for natural language generation in the context of generating online product reviews.
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions.
