activity
20172022
most citedGERE: Generative Evidence Retrieval for Fact Verification

63 citations · 182 across the 16 of their papers we have counts for

collaborators

18 papers

cs.CV2022

Visual Named Entity Linking: A New Dataset and A Baseline

Wenxiang Sun, Yixing Fan, Jiafeng Guo +2

Visual Entity Linking (VEL) is a task to link regions of images with their corresponding entities in Knowledge Bases (KBs), which is beneficial for many computer vision tasks such…

cs.LG20221 cited

LegoNet: A Fast and Exact Unlearning Architecture

Sihao Yu, Fei Sun, Jiafeng Guo +2

Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model. Re-training the model on the retained data after deletion is an…

cs.IR202212 cited

Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models

Chen Wu, Ruqing Zhang, Jiafeng Guo +4

Neural ranking models (NRMs) have achieved promising results in information retrieval. NRMs have also been shown to be vulnerable to adversarial examples. A typical Word Substituti…

cs.IR20223 cited

Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models

Yinqiong Cai, Jiafeng Guo, Yixing Fan +3

Neural ranking models (NRMs) have become one of the most important techniques in information retrieval (IR). Due to the limitation of relevance labels, the training of NRMs heavily…

cs.CL202210 cited

A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration

Shaojie Jiang, Ruqing Zhang, Svitlana Vakulenko +1

The cross-entropy objective has proved to be an all-purpose training objective for autoregressive language models (LMs). However, without considering the penalization of problemati…

cs.IR202233 cited

Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction

Xinyu Ma, Jiafeng Guo, Ruqing Zhang +2

Dense retrieval has shown promising results in many information retrieval (IR) related tasks, whose foundation is high-quality text representation learning for effective search. So…