Fang Ma

2 accepted papers

2022

Structural Bias for Aspect Sentiment Triplet Extraction

Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, Dawei Song

COLING 2022main

Structural bias has recently been exploited for aspect sentiment triplet extraction (ASTE) and led to improved performance. On the other hand, it is recognized that explicitly incorporating structural bias would have a negative impact on efficiency, whereas pretrained language models (PLMs) can alre…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2022

XPrompt: Exploring the Extreme of Prompt Tuning

Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu +2

EMNLP 2022main

Prompt tuning learns soft prompts to condition the frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of fine-tuning as the model scale increases, there is still a large performanc…

Cited by 39 Source ↗PDF ↗Scholar ↗