Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models EACL

Tianxing He | Bryan McCann | Caiming Xiong | Ehsan Hosseini-Asl |

Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models EACL

Tianxing He | Jun Liu | Kyunghyun Cho | Myle Ott | Bing Liu | James Glass | Fuchun Peng |

Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation? EMNLP

Tianxing He | Jingzhao Zhang | Zhiming Zhou | James Glass |

Negative Training for Neural Dialogue Response Generation ACL

Tianxing He | James Glass |

A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation AACL

Moin Nadeem | Tianxing He | Kyunghyun Cho | James Glass |