Projects | Yuqin Zhou

Research

Reinforced Queries using Pre-trained Language Models in Sparse Retrieval

We address the persistent issue of query-document mismatch in sparse retrieval by leveraging reinforcement learning and a pre-trained model.

Towards Language Modeling Using Tensor Trains

Tensor networks are a powerful modeling framework developed for complex quantum systems. We propose a novel Tensor Train Language Model, as an illustration of how tensor networks can be applied to real-world language modeling datasets. The paper is under review in ICML

Courses

Neural Information Retrieval

[14 June 2022] This was my first individual course project in the field of NLP. Fortunately, my model performed best in the Neural information Retrieval course offered in 2022 at the University of Copenhagen.

Features, Architecture, Combine Them Together

[12 June 2022] Word embeddings are powerful even when not accompanied by a neural network model. In this course project, we profiled each Twitter user by word distribution or embeddings, and then did the classfication task by machine learning techniques.