Search Results for author:
Found 13 papers, 3 papers with code
Mitigating the Diminishing Effect of Elastic Weight Consolidation
Elastic weight consolidation (EWC, Kirkpatrick et al. 2017) is a promising approach to addressing catastrophic forgetting in sequential training.
Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model
FEVEROUS is a benchmark and research initiative focused on fact extraction and verification tasks involving unstructured text and structured tabular data.
XFEVER: Exploring Fact Verification across Languages
Experimental results show that the multilingual language model can be used to build fact verification models in different languages efficiently.
Outlier-Aware Training for Improving Group Accuracy Disparities
Methods addressing spurious correlations such as Just Train Twice (JTT, arXiv:2107. 09044v2) involve reweighting a subset of the training set to maximize the worst-group accuracy.
A Multi-Level Attention Model for Evidence-Based Fact Checking
Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources.
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models.
Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling
Exploiting sentence-level labels, which are easy to obtain, is one of the plausible methods to improve low-resource named entity recognition (NER), where token-level labels are costly to annotate.
Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora
Flipping sentiment while preserving sentence meaning is challenging because parallel sentences with the same content but different sentiment polarities are not always available for model learning.
Better Exploiting Latent Variables in Text Modeling
We show that sampling latent variables multiple times at a gradient step helps in improving a variational autoencoder and propose a simple and effective method to better exploit these latent variables through hidden state averaging.
