1 code implementation • 12 Dec 2023 • Yang Trista Cao, Anna Sotnikova, Jieyu Zhao, Linda X. Zou, Rachel Rudinger, Hal Daume III
This raises the question: do stereotypes present in one social context leak across languages within the model?
no code implementations • 12 Nov 2022 • Upol Ehsan, Q. Vera Liao, Samir Passi, Mark O. Riedl, Hal Daume III
We found that the Seamful XAI design process helped users foresee AI harms, identify underlying reasons (seams), locate them in the AI's lifecycle, learn how to leverage seamful information to improve XAI and user agency.
2 code implementations • EMNLP 2018 • Chris Kedzie, Kathleen McKeown, Hal Daume III
We carry out experiments with deep learning models of summarization across the domains of news, personal stories, meetings, and medical articles in order to understand how content selection is performed.
no code implementations • ICML 2017 • Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daume III, John Langford
We design an active learning algorithm for cost-sensitive multiclass classification: problems where different errors have different costs.
no code implementations • ICML 2017 • Hal Daume III, Nikos Karampatziakis, John Langford, Paul Mineiro
Compared to previous approaches, we obtain substantially better statistical performance for two reasons: First, we prove a tighter and more complete boosting theorem, and second we translate the results more directly into an algorithm.
no code implementations • 30 Nov 2015 • Snigdha Chaturvedi, Dan Goldwasser, Hal Daume III
The ability to comprehend wishes or desires and their fulfillment is important to Natural Language Understanding.
no code implementations • 30 Nov 2015 • Snigdha Chaturvedi, Shashank Srivastava, Hal Daume III, Chris Dyer
Studying characters plays a vital role in computationally representing and interpreting narratives.
no code implementations • 26 Oct 2015 • Sudha Rao, Yogarshi Vyas, Hal Daume III, Philip Resnik
We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, a Learning to Search approach, by modeling the concept and the relation learning in a unified framework.
no code implementations • NeurIPS 2014 • He He, Hal Daume III, Jason M. Eisner
Branch-and-bound is a widely used method in combinatorial optimization, including mixed integer programming, structured prediction and MAP inference.
no code implementations • 9 Aug 2014 • Hal Daume III
We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks.
no code implementations • NeurIPS 2013 • Yuening Hu, Jordan L. Ying, Hal Daume III, Z. Irene Ying
Discovering hierarchical regularities in data is a key problem in interacting with large datasets, modeling cognition, and encoding knowledge.
no code implementations • 27 Jun 2012 • Abhishek Kumar, Hal Daume III
In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks.