413 citations · 469 across the 8 of their papers we have counts for
8 papers
Approximating Human-Like Few-shot Learning with GPT-based Compression
Cynthia Huang, Yuqing Xie, Zhiying Jiang +2
In this work, we conceptualize the learning process as information compression. We seek to equip generative pre-trained models with human-like learning capabilities that enable dat…
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
Yi-An Lai, Elman Mansimov, Yuqing Xie +1
When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavio…
An Embedding-Based Grocery Search Model at Instacart
Yuqing Xie, Taesik Na, Xiao Xiao +7
The key to e-commerce search is how to best utilize the large yet noisy log data. In this paper, we present our embedding-based model for grocery search at Instacart. The system le…
Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval
Wei Zhong, Jheng-Hong Yang, Yuqing Xie +1
With the recent success of dense retrieval methods based on bi-encoders, studies have applied this approach to various interesting downstream retrieval tasks with good efficiency a…
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Yuqing Xie, Yi-an Lai, Yuanjun Xiong +2
Behavior of deep neural networks can be inconsistent between different versions. Regressions during model update are a common cause of concern that often over-weigh the benefits in…
Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents
Ruixue Zhang, Wei Yang, Luyun Lin +7
Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations…
Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
Wei Yang, Yuqing Xie, Luchen Tan +3
Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia,…
End-to-End Open-Domain Question Answering with BERTserini
Wei Yang, Yuqing Xie, Aileen Lin +5
We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and…