With endless amounts of data and very limited bandwidth, fast data
compr...
Backpropagation, the cornerstone of deep learning, is limited to computi...
How to train an ideal teacher for knowledge distillation is still an ope...
Practical applications of event extraction systems have long been hinder...
Here, we show that the robust overfitting shall be viewed as the early p...
With recent advances in distantly supervised (DS) relation extraction (R...
Multi-head attention plays a crucial role in the recent success of
Trans...
Identifying and understanding quality phrases from context is a fundamen...
Multiple intriguing problems hover in adversarial training, including
ro...
Our goal is to understand why the robustness drops after conducting
adve...
We explore the application of very deep Transformer models for Neural Ma...
While typical named entity recognition (NER) models require the training...
Transformers have been proved effective for many deep learning tasks.
Tr...
Sequence labeling is a fundamental framework for various natural languag...
Everyone makes mistakes. So do human annotators when curating labels for...
Commonly adopted metrics for extractive text summarization like ROUGE fo...
Taking word sequences as the input, typical named entity recognition (NE...
The learning rate warmup heuristic achieves remarkable success in stabil...
In recent years there is surge of interest in applying distant supervisi...
Distant supervision leverages knowledge bases to automatically label
ins...
Recent advances in deep neural models allow us to build reliable named e...
Many efforts have been made to facilitate natural language processing ta...
Expert finding is an important task in both industry and academia. It is...
Wikidata is the new, large-scale knowledge base of the Wikimedia Foundat...
Linguistic sequence labeling is a general modeling approach that encompa...
Relation extraction is a fundamental task in information extraction. Mos...