Hal Daumé
7 papers in the PaperMetrix corpus
Papers by this author
-
Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks
2018 · arXiv (Cornell University)
Recent results suggest that attacks against supervised machine learning systems are quite effective, while defenses are easily bypassed by new attacks. However, the specifications for machine learning systems currently lack precise adversary definitions, and the …
-
Towards Automatic Generation of Questions from Long Answers
2020 · arXiv (Cornell University)
Automatic question generation (AQG) has broad applicability in domains such as tutoring systems, conversational agents, healthcare literacy, and information retrieval. Existing efforts at AQG have been limited to short answer lengths of up to two …
-
Active Imitation Learning from Multiple Non-Deterministic Teachers:\n Formulation, Challenges, and Algorithms
2020 · arXiv (Cornell University)
We formulate the problem of learning to imitate multiple, non-deterministic\nteachers with minimal interaction cost. Rather than learning a specific policy\nas in standard imitation learning, the goal in this problem is to learn a\ndistribution over a …
-
Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA
2024 · arXiv (Cornell University)
Recent advancements of large language models (LLMs) have led to claims of AI surpassing humans in natural language processing (NLP) tasks such as textual understanding and reasoning. This work investigates these assertions by introducing CAIMIRA, …
-
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
2015
Mohit Iyyer, Varun Manjunatha, Jordan Boyd-Graber, Hal Daumé III. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). …
-
Non-Monotonic Sequential Text Generation
2019 · arXiv (Cornell University)
Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that …
-
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information
2018
Inquiry is fundamental to communication, and machines cannot effectively collaborate with humans unless they can ask questions. In this work, we build a neural network model for the task of ranking clarification questions. Our model …