Publications

. Masked Part-Of-Speech Model: Does modeling long context help unsupervised POS-tagging?. In NAACL, 2022.

Details

. Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning. In ACL Findings, 2022.

Details PDF Code

. GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models. Preprint in Arxiv, 2022.

Details PDF Code

. Hidden Biases in Unreliable News Detection Datasets. (Best Long Paper Award Honorable Mention) In EACL, 2021.

Details PDF Code

. The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions. In EMNLP, 2020.

Details PDF Code

. What Can We Learn from Collective Human Opinions on Natural Language Inference Data?. In EMNLP, 2020.

Details PDF Code

. Towards Robustifying NLI Models Against Lexical Dataset Biases. In ACL, 2020.

Details PDF Code

. Affordable On-line Dialogue Policy Learning. In EMNLP, 2017.

Details PDF Appendix

. Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning. In EMNLP, 2017.

Details PDF Appendix

. On-line Dialogue Policy Learning with Companion Teaching. In EACL, 2017.

Details PDF