Ji Xin

发表

Improving Neural Fine-Grained Entity Typing With Knowledge Attention

Zhiyuan Liu, Maosong Sun, Ji Xin, 2018, AAAI.

Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking

Jimmy J. Lin, Ji Xin, Xinyu Zhang, 2022, EMNLP.

Few-Shot Non-Parametric Learning with Deep Latent Variable Model

Ming Li, Ji Xin, Zhiying Jiang, 2022, 2206.11573.

Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers

Yaoliang Yu, Ji Xin, Zhiying Jiang, 2022, ArXiv.

Few-Shot Non-Parametric Learning with Deep Latent Variable Model

Ming Li, Ji Xin, Jimmy Lin, 2022, ArXiv.

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference pdf

Jimmy J. Lin, Yaoliang Yu, Ji Xin, 2020, ACL.

Early Exiting BERT for Efficient Document Ranking

Jimmy J. Lin, Yaoliang Yu, Ji Xin, 2020, SUSTAINLP.

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

Jimmy J. Lin, Ji Xin, Raphael Tang, 2021, BLACKBOXNLP.

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

Jimmy J. Lin, Yaoliang Yu, Jimmy Lin, 2021, EACL.

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

Jimmy J. Lin, Jimmy Lin, Kai Sun, 2021, EMNLP.

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

Jimmy J. Lin, Yaoliang Yu, Jimmy Lin, 2021, ACL.

Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations pdf

Ashwin Srinivasan, Paul N. Bennett, Chenyan Xiong, 2021, FINDINGS.

Serverless BM25 Search and BERT Reranking

Jimmy J. Lin, Jimmy Lin, Ji Xin, 2021, DESIRES.

Approach Zero and Anserini at the CLEF-2021 ARQMath Track: Applying Substructure Search and BM25 on Operator Tree Path Tokens

Jimmy J. Lin, Richard Zanibbi, Jimmy Lin, 2021, CLEF.

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

Jimmy J. Lin, Yaoliang Yu, Jimmy Lin, 2019, EMNLP.

Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits pdf

Jimmy J. Lin, Yaoliang Yu, Jimmy Lin, 2019, ArXiv.

Inserting Information Bottleneck for Attribution in Transformers

Jimmy J. Lin, Ji Xin, Jimmy Lin, 2020, FINDINGS.

Approach Zero and Anserini at the CLEF-2021 ARQMath Track: Applying Substructure Search and BM25 on Operator Tree Path Tokens

Jimmy J. Lin, R. Zanibbi, Ji Xin, 2021, Conference and Labs of the Evaluation Forum.