Skip to main content
Search

Khai Phan Tran

1 related articles

Subscribe to updates
  1. arXiv

    Document-level relation extraction drops iterative denoising: Syn2DRE's dual teachers cross-teach, training in 26 hours with 30,480 unlabeled documents

    Document-level relation extraction must judge relations between entity pairs across sentences, and high-quality annotation is expensive, while pseudo-labeling methods often need repeated training and denoising and can reinforce their own errors. Syn2DRE places two differently structured teacher-student networks in a single training run: each teacher follows its student by exponential moving average, keeps only pseudo-labels with the lowest prediction variance, and the two teachers exchange high-confidence labels where their predictions disagree. On Re-DocRED it reaches 79.53/79.40 dev/test F1 against UGDRE's 78.28/78.14, and trains in 26 hours using 30,480 unlabeled documents, against 55 hours and 101,873 documents for UGDRE.

You’re all caught up