Yuqing Xie

Yuqing Xie

Auto-generated profile, based on publicly available information

Yuqing Xie

University of Waterloo

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022
Verified
Conference Paper
Open access
PDF file
WZWei Zhong
Wei Zhong
JYJheng-Hong Yang
Jheng-Hong Yang
YXYuqing Xie
Yuqing Xie
JLJimmy Lin
Jimmy Lin
Wei Zhong, Jheng-Hong Yang, Yuqing Xie, Jimmy Lin. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022.

1 January 2021
Verified
Conference Paper
Open access
PDF file
YXYuqing Xie
Yuqing Xie
YLYi-An Lai
Yi-An Lai
YXYuanjun Xiong
Yuanjun Xiong
YZYi Zhang
Yi Zhang
SSStefano Soatto
Stefano Soatto
Yuqing Xie, Yi-An Lai, Yuanjun Xiong, Yi Zhang, Stefano Soatto. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

1 January 2023
Verified
Conference Paper
Open access
PDF file
YLYi-An Lai
Yi-An Lai
EMElman Mansimov
Elman Mansimov
YXYuqing Xie
Yuqing Xie
YZYi Zhang
Yi Zhang
Yi-An Lai, Elman Mansimov, Yuqing Xie, Yi Zhang. Findings of the Association for Computational Linguistics: EACL 2023. 2023.


21 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
WZWei Zhong
Wei Zhong
JYJheng-Hong Yang
Jheng-Hong Yang
YXYuqing Xie
Yuqing Xie
JLJimmy Lin
Jimmy Lin
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 and in-domain effectiveness. Recently, we have also seen the presence of dense retrieval models in Math Information Retrieval (MIR) tasks, but the most effective systems remain classic retrieval methods that consider hand-crafted structure features. In this work, we try to combine the best of both worlds:\ a well-defined structure search method for effective formula search and efficient bi-encoder dense retrieval models to capture contextual similarities. Specifically, we have evaluated two representative bi-encoder models for token-level and passage-level dense retrieval on recent MIR tasks. Our results show that bi-encoder models are highly complementary to existing structure search methods, and we are able to advance the state-of-the-art on MIR datasets.

14 August 2023 in arXiv
Verified
Preprint
Open access
PDF file
CHCynthia Huang
Cynthia Huang
YXYuqing Xie
Yuqing Xie
ZJZhiying Jiang
Zhiying Jiang
JLJimmy Lin
Jimmy Lin
MLMing Li
Ming Li
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 data compression during inference. We present a novel approach that utilizes the Generative Pre-trained Transformer (GPT) to approximate Kolmogorov complexity, with the aim of estimating the optimal Information Distance for few-shot learning. We first propose using GPT as a prior for lossless text compression, achieving a noteworthy compression ratio. Experiment with LLAMA2-7B backbone achieves a compression ratio of 15.5 on enwik9. We justify the pre-training objective of GPT models by demonstrating its equivalence to the compression length, and, consequently, its ability to approximate the information distance for texts. Leveraging the approximated information distance, our method allows the direct application of GPT models in quantitative text similarity measurements. Experiment results show that our method overall achieves superior performance compared to embedding and prompt baselines on challenging NLP tasks, including semantic similarity, zero and one-shot text classification, and zero-shot text ranking.