BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression EACL

Ji Xin | Raphael Tang | Yaoliang Yu | Jimmy Lin |

Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval EMNLP

Xueguang Ma | Minghan Li | Kai Sun | Ji Xin | Jimmy Lin |

Bag-of-Words Baselines for Semantic Code Search ACL IJCNLP NLP4Prog

Xinyu Zhang | Ji Xin | Andrew Yates | Jimmy Lin |

Voice Query Auto Completion EMNLP

Raphael Tang | Karun Kumar | Kendra Chalkley | Ji Xin | Liming Zhang | Wenyan Li | Gefei Yang | Yajie Mao | Junho Shin | Geoffrey Craig Murray | Jimmy Lin |

How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks BlackboxNLP EMNLP

Zhiying Jiang | Raphael Tang | Ji Xin | Jimmy Lin |

The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing ACL IJCNLP

Ji Xin | Raphael Tang | Yaoliang Yu | Jimmy Lin |

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference ACL

Ji Xin | Raphael Tang | Jaejun Lee | Yaoliang Yu | Jimmy Lin |

Showing Your Work Doesn’t Always Work ACL

Raphael Tang | Jaejun Lee | Ji Xin | Xinyu Liu | Yaoliang Yu | Jimmy Lin |

Early Exiting BERT for Efficient Document Ranking EMNLP sustainlp

Ji Xin | Rodrigo Nogueira | Yaoliang Yu | Jimmy Lin |

Inserting Information Bottlenecks for Attribution in Transformers EMNLP Findings

Zhiying Jiang | Raphael Tang | Ji Xin | Jimmy Lin |

What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons EMNLP

Ji Xin | Jimmy Lin | Yaoliang Yu |

Put It Back: Entity Typing with Language Model Enhancement EMNLP

Ji Xin | Hao Zhu | Xu Han | Zhiyuan Liu | Maosong Sun |