Improving named entity recognition by external context retrieving and cooperative learning

X Wang, Y Jiang, N Bach, T Wang, Z Huang… - arXiv preprint arXiv …, 2021 - arxiv.org
Recent advances in Named Entity Recognition (NER) show that document-level contexts
can significantly improve model performance. In many application scenarios, however, such …

A neural span-based continual named entity recognition model

Y Zhang, Q Chen - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Abstract Named Entity Recognition (NER) models capable of Continual Learning (CL) are
realistically valuable in areas where entity types continuously increase (eg, personal …

Measuring and reducing model update regression in structured prediction for NLP

D Cai, E Mansimov, YA Lai, Y Su… - Advances in Neural …, 2022 - proceedings.neurips.cc
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 …

Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training

Z Zhang, E Strubell, E Hovy - arXiv preprint arXiv:2305.12634, 2023 - arxiv.org
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 …

Language modelling via learning to rank

A Frydenlund, G Singh, F Rudzicz - … of the AAAI conference on artificial …, 2022 - ojs.aaai.org
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 …

A Simple Yet Effective Approach to Structured Knowledge Distillation

W Lin, Y Li, L Liu, S Shi… - ICASSP 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
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 …

Compression Models via Meta-Learning and Structured Distillation for Named Entity Recognition

Q Zhang, Z Gao, M Zhang, J Duan… - … Conference on Asian …, 2023 - ieeexplore.ieee.org
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 …

[PDF][PDF] Exploring Language Structured Prediction in Resource-limited Scenarios

Z Zhang - 2023 - lti.cmu.edu
In natural language processing (NLP), many tasks involve structured prediction: predicting
structured outputs consisting of a group of interdependent variables. This allows extracting …

LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints

W Xu, J Wang, L Xie, J He, H Zhou, T Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
Integrating first-order logic constraints (FOLCs) with neural networks is a crucial but
challenging problem since it involves modeling intricate correlations to satisfy the …

An Efficient Mean-field Approach to High-Order Markov Logic

W Xu, J He, J Wang, H Zhou, X Wan, T Wang, R Li… - openreview.net
Markov logic networks (MLNs) are powerful models for symbolic reasoning, which combine
probabilistic modeling with relational logic. Inference algorithms for MLNs often perform at …