DeepAI AI Chat
Log In Sign Up

Improving Generalization in Coreference Resolution via Adversarial Training

by   Sanjay Subramanian, et al.
University of Pennsylvania

In order for coreference resolution systems to be useful in practice, they must be able to generalize to new text. In this work, we demonstrate that the performance of the state-of-the-art system decreases when the names of PER and GPE named entities in the CoNLL dataset are changed to names that do not occur in the training set. We use the technique of adversarial gradient-based training to retrain the state-of-the-art system and demonstrate that the retrained system achieves higher performance on the CoNLL dataset (both with and without the change of named entities) and the GAP dataset.


page 1

page 2

page 3

page 4


Improving the Quality of Neural Machine Translation Through Proper Translation of Name Entities

In this paper, we have shown a method of improving the quality of neural...

Building Language Models for Text with Named Entities

Text in many domains involves a significant amount of named entities. Pr...

Bridging the Performance Gap between FGSM and PGD Adversarial Training

Deep learning achieves state-of-the-art performance in many tasks but ex...

A Generalized Vector Space Model for Ontology-Based Information Retrieval

Named entities (NE) are objects that are referred to by names such as pe...

Clustering Prominent People and Organizations in Topic-Specific Text Corpora

Named entities in text documents are the names of people, organization, ...

Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition

Named Entity Recognition (NER) systems often demonstrate great performan...

UPTON: Unattributable Authorship Text via Data Poisoning

In online medium such as opinion column in Bloomberg, The Guardian and W...