Search Results for author:
Found 2 papers, 0 papers with code
Label Correction Model for Aspect-based Sentiment Analysis
Specifically, given an input sentence, our model first predicts the aspect boundary label sequence and sentiment label sequence, then re-predicts the aspect boundary (sentiment) label sequence using the embeddings of the previously predicted sentiment (aspect boundary) label.
Progressive Self-Training with Discriminator for Aspect Term Extraction
In this paper, we use two means to alleviate the noise in the pseudo-labels.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
