activity
20192024
most citedCodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

416 citations · 585 across the 38 of their papers we have counts for

collaborators
Showing cs.IRShow all

6 papers · 1 filter

cs.IR2023

RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation

Ning Wu, Ming Gong, Linjun Shou +2

Online recommender systems (RS) aim to match user needs with the vast amount of resources available on various platforms. A key challenge is to model user preferences accurately un…

cs.IR2023

Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval

Shengyao Zhuang, Linjun Shou, Jian Pei +4

Current dense retrievers (DRs) are limited in their ability to effectively process misspelled queries, which constitute a significant portion of query traffic in commercial search…

cs.IR2023

Empowering Dual-Encoder with Query Generator for Cross-Lingual Dense Retrieval

Houxing Ren, Linjun Shou, Ning Wu +2

In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance…

cs.IR2023

Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval

Houxing Ren, Linjun Shou, Jian Pei +3

Recent multilingual pre-trained models have shown better performance in various multilingual tasks. However, these models perform poorly on multilingual retrieval tasks due to lack…

cs.IR20221 cited

Transformer-Empowered Content-Aware Collaborative Filtering

Weizhe Lin, Linjun Shou, Ming Gong +4

Knowledge graph (KG) based Collaborative Filtering is an effective approach to personalizing recommendation systems for relatively static domains such as movies and books, by lever…

cs.IR20209 cited

Mining Implicit Relevance Feedback from User Behavior for Web Question Answering

Linjun Shou, Shining Bo, Feixiang Cheng +3

Training and refreshing a web-scale Question Answering (QA) system for a multi-lingual commercial search engine often requires a huge amount of training examples. One principled id…