research
∙
06/02/2023
DocFormerv2: Local Features for Document Understanding
We propose DocFormerv2, a multi-modal transformer for Visual Document Un...
share
research
∙
10/27/2021
Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection
Anomaly detection or outlier detection is a common task in various domai...
research
∙
09/23/2021
Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords
We present a method for exploring regions around individual points in a ...
research
∙
06/27/2021
A Closer Look at How Fine-tuning Changes BERT
Given the prevalence of pre-trained contextualized representations in to...
research
∙
04/13/2021
DirectProbe: Studying Representations without Classifiers
Understanding how linguistic structures are encoded in contextualized em...
research
∙
09/02/2020
A Simple Global Neural Discourse Parser
Discourse parsing is largely dominated by greedy parsers with manually-d...
research
∙
10/05/2019