activity
20192022
most citedDeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

19 citations · 21 across the 5 of their papers we have counts for

collaborators

6 papers

cs.IR2022

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

Minghan Li, Xinyu Zhang, Ji Xin +2

In information retrieval (IR), candidate set pruning has been commonly used to speed up two-stage relevance ranking. However, such an approach lacks accurate error control and ofte…

cs.IR2021

Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations

Ji Xin, Chenyan Xiong, Ashwin Srinivasan +3

Dense retrieval (DR) methods conduct text retrieval by first encoding texts in the embedding space and then matching them by nearest neighbor search. This requires strong locality…

cs.CL2020

Inserting Information Bottlenecks for Attribution in Transformers

Zhiying Jiang, Raphael Tang, Ji Xin +1

Pretrained transformers achieve the state of the art across tasks in natural language processing, motivating researchers to investigate their inner mechanisms. One common direction…

cs.CL20201 cited

Showing Your Work Doesn't Always Work

Raphael Tang, Jaejun Lee, Ji Xin +3

In natural language processing, a recently popular line of work explores how to best report the experimental results of neural networks. One exemplar publication, titled "Show Your…

cs.CL202019 cited

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Ji Xin, Raphael Tang, Jaejun Lee +2

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which…

cs.SE20191 cited

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

Achyudh Ram, Ji Xin, Meiyappan Nagappan +4

Public vulnerability databases such as CVE and NVD account for only 60% of security vulnerabilities present in open-source projects, and are known to suffer from inconsistent quali…