Recent advances in Named Entity Recognition (NER) show that document-level contexts
can significantly improve model performance. In many application scenarios, however, such …

Abstract Named Entity Recognition (NER) models capable of Continual Learning (CL) are
realistically valuable in areas where entity types continuously increase (eg, personal …

Recent advance in deep learning has led to rapid adoption of machine learning based NLP
models in a wide range of applications. Despite the continuous gain in accuracy, backward …

In this work we propose a pragmatic method that reduces the annotation cost for structured
label spaces using active learning. Our approach leverages partial annotation, which …

We consider language modelling (LM) as a multi-label structured prediction task by re-
framing training from solely predicting a single ground-truth word to ranking a set of words …

Structured prediction models aim at solving tasks where the output is a complex structure,
rather than a single variable. Performing knowledge distillation for such problems is non …

This paper addresses the issue of high resource consumption in named entity recognition
(NER) under large models by utilizing meta-learning and structured distillation to generate …

In natural language processing (NLP), many tasks involve structured prediction: predicting
structured outputs consisting of a group of interdependent variables. This allows extracting …

Integrating first-order logic constraints (FOLCs) with neural networks is a crucial but
challenging problem since it involves modeling intricate correlations to satisfy the …

Markov logic networks (MLNs) are powerful models for symbolic reasoning, which combine
probabilistic modeling with relational logic. Inference algorithms for MLNs often perform at …