Kianté Brantley

Also published as: Kiante Brantley


pdf bib
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing
Kianté Brantley | Soham Dan | Iryna Gurevych | Ji-Ung Lee | Filip Radlinski | Hinrich Schütze | Edwin Simpson | Lili Yu
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing


pdf bib
Active Imitation Learning with Noisy Guidance
Kianté Brantley | Amr Sharaf | Hal Daumé III
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Imitation learning algorithms provide state-of-the-art results on many structured prediction tasks by learning near-optimal search policies. Such algorithms assume training-time access to an expert that can provide the optimal action at any queried state; unfortunately, the number of such queries is often prohibitive, frequently rendering these approaches impractical. To combat this query complexity, we consider an active learning setting in which the learning algorithm has additional access to a much cheaper noisy heuristic that provides noisy guidance. Our algorithm, LEAQI, learns a difference classifier that predicts when the expert is likely to disagree with the heuristic, and queries the expert only when necessary. We apply LEAQI to three sequence labelling tasks, demonstrating significantly fewer queries to the expert and comparable (or better) accuracies over a passive approach.


Non-Monotonic Sequential Text Generation
Kiante Brantley | Kyunghyun Cho | Hal Daumé | Sean Welleck
Proceedings of the 2019 Workshop on Widening NLP

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 operate in non-monotonic orders; the model directly learns good orders, without any additional annotation. Our framework operates by generating a word at an arbitrary position, and then recursively generating words to its left and then words to its right, yielding a binary tree. Learning is framed as imitation learning, including a coaching method which moves from imitating an oracle to reinforcing the policy’s own preferences. Experimental results demonstrate that using the proposed method, it is possible to learn policies which generate text without pre-specifying a generation order while achieving competitive performance with conventional left-to-right generation.


pdf bib
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task
Amr Sharaf | Shi Feng | Khanh Nguyen | Kianté Brantley | Hal Daumé III
Proceedings of the Second Conference on Machine Translation