no code implementations • NAACL (ACL) 2022 • Jordan Boyd-Graber, Samuel Carton, Shi Feng, Q. Vera Liao, Tania Lombrozo, Alison Smith-Renner, Chenhao Tan
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.
no code implementations • 23 May 2022 • Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton, Chenhao Tan
Despite the strong performance of current NLP models, they can be brittle against adversarial attacks.
no code implementations • 25 Apr 2022 • Vivian Lai, Samuel Carton, Rajat Bhatnagar, Q. Vera Liao, Yunfeng Zhang, Chenhao Tan
Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples.
1 code implementation • Findings (ACL) 2022 • Samuel Carton, Surya Kanoria, Chenhao Tan
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.
1 code implementation • EMNLP 2020 • Samuel Carton, Anirudh Rathore, Chenhao Tan
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.
no code implementations • ACL 2021 • Cristina Garbacea, Mengtian Guo, Samuel Carton, Qiaozhu Mei
Text simplification reduces the language complexity of professional content for accessibility purposes.
no code implementations • 16 Mar 2020 • Vivian Lai, Samuel Carton, Chenhao Tan
Machine learning models are increasingly integrated into societally critical applications such as recidivism prediction and medical diagnosis, thanks to their superior predictive power.
1 code implementation • IJCNLP 2019 • Cristina Garbacea, Samuel Carton, Shiyan Yan, Qiaozhu Mei
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.
no code implementations • EMNLP 2018 • Samuel Carton, Qiaozhu Mei, Paul Resnick
We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions.