Papers by Yinhao Wu
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on what to generate but ignore what not to generate . a template-agnostic method boosts original learning and reduces mistakes simultaneously . |
| Approach: | They propose a template-agnostic method to control the token-level generation . they introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models . |
| Outcome: | The proposed method boosts original learning and reduces mistakes simultaneously on four public datasets. |
Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on aspect sentiment quad prediction (ASQP) uses a template to extract aspect quadruplets from review sentences. |
| Approach: | They propose to use a pre-trained language model to select proper orders from a template order perspective to improve aspect sentiment quad prediction. |
| Outcome: | The proposed method outperforms state-of-the-art methods significantly in low-resource settings. |
Guidelines as Environments: A World Model Approach to Rule Following (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models for guideline-following are a poor fit for ambiguous, text-defined constraints. |
| Approach: | They propose a Rule-Grounded Causal World Model that builds an explicit state space from guideline text itself. |
| Outcome: | Experiments show that the proposed model can be used to model rule execution with an explicit state space from the guideline text itself. |