Towards Robustifying NLI Models Against Lexical Dataset Biases ACL

Xiang Zhou | Mohit Bansal |

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

Xiang Zhou | Yixin Nie | Hao Tan | Mohit Bansal |

What Can We Learn from Collective Human Opinions on Natural Language Inference Data? EMNLP

Yixin Nie | Xiang Zhou | Mohit Bansal |

Affordable On-line Dialogue Policy Learning EMNLP

Cheng Chang | Runzhe Yang | Lu Chen | Xiang Zhou | Kai Yu |

Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning EMNLP

Lu Chen | Xiang Zhou | Cheng Chang | Runzhe Yang | Kai Yu |

On-line Dialogue Policy Learning with Companion Teaching EACL

Lu Chen | Runzhe Yang | Cheng Chang | Zihao Ye | Xiang Zhou | Kai Yu |