Search Results for author: Thomas Schaaf

Found 5 papers, 3 papers with code

Effective Convolutional Attention Network for Multi-label Clinical Document Classification

no code implementations EMNLP 2021 Yang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf

Multi-label document classification (MLDC) problems can be challenging, especially for long documents with a large label set and a long-tail distribution over labels.

Classification Document Classification +1

Revisiting text decomposition methods for NLI-based factuality scoring of summaries

no code implementations30 Nov 2022 John Glover, Federico Fancellu, Vasudevan Jagannathan, Matthew R. Gormley, Thomas Schaaf

In this paper we systematically compare different granularities of decomposition -- from document to sub-sentence level, and we show that the answer is no.

Natural Language Inference Sentence

AdaFocal: Calibration-aware Adaptive Focal Loss

1 code implementation21 Nov 2022 Arindam Ghosh, Thomas Schaaf, Matthew R. Gormley

In this paper, we propose a calibration-aware adaptive focal loss called AdaFocal that utilizes the calibration properties of focal (and inverse-focal) loss and adaptively modifies $\gamma_t$ for different groups of samples based on $\gamma_{t-1}$ from the previous step and the knowledge of model's under/over-confidence on the validation set.

Out-of-Distribution Detection

Posterior Calibrated Training on Sentence Classification Tasks

1 code implementation ACL 2020 Taehee Jung, Dongyeop Kang, Hua Cheng, Lucas Mentch, Thomas Schaaf

Here we propose an end-to-end training procedure called posterior calibrated (PosCal) training that directly optimizes the objective while minimizing the difference between the predicted and empirical posterior probabilities. We show that PosCal not only helps reduce the calibration error but also improve task performance by penalizing drops in performance of both objectives.

Classification General Classification +2

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