Search Results for author:
Found 9 papers, 5 papers with code
Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with Pseudowords
We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses.
DocFormerv2: Local Features for Document Understanding
We propose DocFormerv2, a multi-modal transformer for Visual Document Understanding (VDU).
Ranked #9 on
Visual Question Answering (VQA)
on DocVQA test
(using extra training data)
Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection
Anomaly detection or outlier detection is a common task in various domains, which has attracted significant research efforts in recent years.
Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords
We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses.
A Closer Look at How Fine-tuning Changes BERT
Given the prevalence of pre-trained contextualized representations in today's NLP, there have been many efforts to understand what information they contain, and why they seem to be universally successful.
DirectProbe: Studying Representations without Classifiers
Understanding how linguistic structures are encoded in contextualized embedding could help explain their impressive performance across NLP@.
A Simple Global Neural Discourse Parser
Discourse parsing is largely dominated by greedy parsers with manually-designed features, while global parsing is rare due to its computational expense.
On the Limits of Learning to Actively Learn Semantic Representations
We conclude that the current applicability of LTAL for improving data efficiency in learning semantic meaning representations is limited.
Learning Semantic Representations
Natural Language Understanding
Beyond Context: A New Perspective for Word Embeddings
We define a new modeling framework for training word embeddings that captures this intuition.
