20 citations · 83 across the 17 of their papers we have counts for
6 papers · 1 filter
Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs
Biyang Guo, He Wang, Wenyilin Xiao +4
In the burgeoning field of Large Language Models (LLMs) like ChatGPT and LLaMA, Prompt Engineering (PE) is renowned for boosting zero-shot or in-context learning (ICL) through prom…
GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation
Biyang Guo, Yeyun Gong, Yelong Shen +4
We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual s…
IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification
Ziyuan Wang, Hailiang Huang, Songqiao Han
Current text classification methods typically encode the text merely into embedding before a naive or complicated classifier, which ignores the suggestive information contained in…
Selective Text Augmentation with Word Roles for Low-Resource Text Classification
Biyang Guo, Songqiao Han, Hailiang Huang
Data augmentation techniques are widely used in text classification tasks to improve the performance of classifiers, especially in low-resource scenarios. Most previous methods con…
American Hate Crime Trends Prediction with Event Extraction
Songqiao Han, Hailiang Huang, Jiangwei Liu +1
Social media platforms may provide potential space for discourses that contain hate speech, and even worse, can act as a propagation mechanism for hate crimes. The FBI's Uniform Cr…
What Have Been Learned & What Should Be Learned? An Empirical Study of How to Selectively Augment Text for Classification
Biyang Guo, Sonqiao Han, Hailiang Huang
Text augmentation techniques are widely used in text classification problems to improve the performance of classifiers, especially in low-resource scenarios. Whilst lots of creativ…