Guo‐qing Zheng

A Conditional Generative Matching Model for Multi-lingual Reply Suggestion

2021 · arXiv (Cornell University)

We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus …

Pathologies of Pre-trained Language Models in Few-shot Fine-tuning

2022

Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from. In this work, we propose to answer …

Learning to Reweight Terms with Distributed Representations

2015

Term weighting is a fundamental problem in IR research and numerous weighting models have been proposed. Proper term weighting can greatly improve retrieval accuracies, which essentially involves two types of query understanding: interpreting the query …