Ji Xin
19 papers · 2018–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (7) π Academic Marathon (5) π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (47)
πΊοΈ
Taxonomy Completionist
(47)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(17)
π§¬
Topic Evolution
π
Keyword Champion
(2)
β‘
Prolific Year
(8)
π
Century Club
(19)
π₯
Unstoppable
(6)
ποΈ
Keyword Collector
(91)
π
Trend Setter
β
The Questioner
(3)
Conferences
EMNLP (8)
ACL (6)
IJCNLP (3)
EACL (1)
NIPS (1)
Top co-authors
Keywords
model compression
(4)
early exiting
(3)
information bottleneck
(2)
natural language query
(2)
neuron-label affinity
(2)
semantic code search
(2)
long short-term memory
(2)
neural network interpretability
(2)
confidence estimation
(2)
neuron analysis
(2)
knowledge distillation
(2)
label-specialized neuron
(2)
error regularization
(2)
bert model
(2)
early exit
(2)
inference acceleration
(2)
selective prediction
(2)
classifier cascade
(2)
passage retrieval
(1)
variational inference
(1)
Papers
Operator Selection and Ordering in a Pipeline Approach to Efficiency Optimizations for Transformers
ACL 2023
Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking
EMNLP 2022
Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
ACL 2022
Few-Shot Non-Parametric Learning with Deep Latent Variable Model
NIPS 2022
Bag-of-Words Baselines for Semantic Code Search
IJCNLP 2021
The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing
ACL 2021
Bag-of-Words Baselines for Semantic Code Search
ACL 2021
BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression
EACL 2021
Voice Query Auto Completion
EMNLP 2021
Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval
EMNLP 2021
How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks
EMNLP 2021
The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing
IJCNLP 2021
Early Exiting BERT for Efficient Document Ranking
EMNLP 2020
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
ACL 2020
Showing Your Work Doesnβt Always Work
ACL 2020
Inserting Information Bottlenecks for Attribution in Transformers
EMNLP 2020
What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons
IJCNLP 2019
What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons
EMNLP 2019
Put It Back: Entity Typing with Language Model Enhancement
EMNLP 2018