Search Results for author: Xiaohui Song

Found 4 papers, 3 papers with code

BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation

1 code implementation19 Jun 2024 Minchong Li, Feng Zhou, Xiaohui Song

The BiLD loss filters out the long-tail noise by utilizing only top-$k$ teacher and student logits, and leverages the internal logits ranking information by constructing logits differences.

Knowledge Distillation Language Modelling +1

Data Augmentation for Copy-Mechanism in Dialogue State Tracking

no code implementations22 Feb 2020 Xiaohui Song, Liangjun Zang, Yipeng Su, Xing Wu, Jizhong Han, Songlin Hu

While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap between seen slot values (i. e., values that occur in both training set and test set) and unseen ones (values that occur in training set but not in test set).

Data Augmentation Dialogue State Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.