Search Results for author:
Found 11 papers, 4 papers with code
Are Prompt-based Models Clueless?
However, models with a task-specific head require a lot of training data, making them susceptible to learning and exploiting dataset-specific superficial cues that do not generalize to other datasets.
Two Training Strategies for Improving Relation Extraction over Universal Graph
This paper explores how the Distantly Supervised Relation Extraction (DS-RE) can benefit from the use of a Universal Graph (UG), the combination of a Knowledge Graph (KG) and a large-scale text collection.
On the Subcategories of n-Torsionfree Modules and Related Modules
Let R be a commutative noetherian ring.
Commutative Algebra Representation Theory 13C60, 13D02
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
Modeling Event Salience in Narratives via Barthes' Cardinal Functions
Events in a narrative differ in salience: some are more important to the story than others.
An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
This study addresses two underexplored issues on CDA, that is, how to reduce the computational cost of data augmentation and how to ensure the quality of the generated data.
Word Rotator's Distance
Accordingly, we propose a method that first decouples word vectors into their norm and direction, and then computes alignment-based similarity using earth mover's distance (i. e., optimal transport cost), which we refer to as word rotator's distance.
Distantly Supervised Biomedical Knowledge Acquisition via Knowledge Graph Based Attention
In this work, we firstly investigate the feasibility of this framework on scientific dataset, specifically on biomedical dataset.
Data Augmentation using Random Image Cropping and Patching for Deep CNNs
We also confirmed that deep CNNs with RICAP achieve better results on classification tasks using CIFAR-100 and ImageNet and an image-caption retrieval task using Microsoft COCO.
Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base.
A Novel Weight-Shared Multi-Stage CNN for Scale Robustness
The proposed WSMS-Net is easily combined with existing deep CNNs such as ResNet and DenseNet and enables them to acquire robustness to object scaling.
