most citedDon't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

6 citations · 24 across the 10 of their papers we have counts for

collaborators

10 papers

cs.CL2023★ 1 cited

Lexical Entrainment for Conversational Systems

Zhengxiang Shi, Procheta Sen, Aldo Lipani

Conversational agents have become ubiquitous in assisting with daily tasks, and are expected to possess human-like features. One such feature is lexical entrainment (LE), a phenome…

cs.CL2023★ 1 cited

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Zhengxiang Shi, Aldo Lipani

Prompt tuning (PT), where a small amount of trainable soft (continuous) prompt vectors is affixed to the input of language models (LM), has shown promising results across various t…

cs.CL2023

Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis

Zhengxiang Shi, Aldo Lipani

In recent years, language models (LMs) have made remarkable progress in advancing the field of natural language processing (NLP). However, the impact of data augmentation (DA) tech…

cs.IR2023★ 4 cited

Self Contrastive Learning for Session-based Recommendation

Zhengxiang Shi, Xi Wang, Aldo Lipani

Session-based recommendation, which aims to predict the next item of users' interest as per an existing sequence interaction of items, has attracted growing applications of Contras…

cs.CL2023★ 3 cited

Rethinking Semi-supervised Learning with Language Models

Zhengxiang Shi, Francesco Tonolini, Nikolaos Aletras +3

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks…

cs.CL2023★ 3 cited

When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge Solution

Zhengxiang Shi, Jerome Ramos, To Eun Kim +3

In collaborative tasks, effective communication is crucial for achieving joint goals. One such task is collaborative building where builders must communicate with each other to con…