Search Results for author:
Found 5 papers, 5 papers with code
BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction
To tackle this issue, we further propose a Broadview Soft Prompting (BvSP) method that aggregates multiple templates with a broader view by taking into account the correlation between the different templates.
Coreference Graph Guidance for Mind-Map Generation
Then we employ a coreference graph encoder to mine the potential governing relations between sentences.
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction
We further propose marginalized unlikelihood learning to suppress the uncertainty-aware mistake tokens.
Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation
By fine-tuning the pre-trained language model with these template orders, our approach improves the performance of quad prediction, and outperforms state-of-the-art methods significantly in low-resource settings.
Ranked #3 on
Aspect-Based Sentiment Analysis (ABSA)
on ACOS
Classical Sequence Match is a Competitive Few-Shot One-Class Learner
Nowadays, transformer-based models gradually become the default choice for artificial intelligence pioneers.
