Style transfer as data augmentation: A case study on named entity recognition

S Chen, L Neves, T Solorio - arXiv preprint arXiv:2210.07916, 2022 - arxiv.org
… on data augmentation still remains understudied by the NLP community. To facilitate
research in this direction, we study style transfer as data augmentation and propose a novel

Leveraging expert guided adversarial augmentation for improving generalization in named entity recognition

A Reich, J Chen, A Agrawal, Y Zhang… - arXiv preprint arXiv …, 2022 - arxiv.org
Named Entity Recognition (NER) systems often demonstrate great performance on in-distribution
data, but … (as high or low) and making small corrections. Before annotating the full set of …

[HTML][HTML] Improving the recall of biomedical named entity recognition with label re-correction and knowledge distillation

H Zhou, Z Liu, C Lang, Y Xu, Y Lin, J Hou - BMC bioinformatics, 2021 - Springer
… a novel Biomedical Named Entity Recognition (BioNER) framework with label re-correction
and … -task learning could improve performance to a certain extent though data augmentation. …

[PDF][PDF] Transfer Learning for Historical Corpora: An Assessment on Post-OCR Correction and Named Entity Recognition.

K Todorov, G Colavizza - CHR, 2020 - ceur-ws.org
augment the dataset by adding OverProof data1 in English. We use 100% of ICDAR2017’s
and Overproof’s data as training data. … to the inclusion of novel deep learning techniques and …

[HTML][HTML] Terminologies augmented recurrent neural network model for clinical named entity recognition

I Lerner, N Paris, X Tannier - Journal of biomedical informatics, 2020 - Elsevier
Objective We aimed to enhance the performance of a supervised model for clinical named-entity
recognition (NER) using medical terminologies. In order to evaluate our system in …

Context-aware adversarial training for name regularity bias in named entity recognition

A Ghaddar, P Langlais, A Rashid… - Transactions of the …, 2021 - direct.mit.edu
… In Section 5, we present a novel adversarial training method … resolution, and grammar error
correction has a negative impact … , we propose a data augmentation approach that introduces …

[HTML][HTML] A survey on Named Entity Recognition—datasets, tools, and methodologies

B Jehangir, S Radhakrishnan, R Agarwal - Natural Language Processing …, 2023 - Elsevier
… The timeline of the research articles used in this work spans from the initial usage of the
technology to present-day novel techniques proposed in various domains such as biomedical …

Data augmentation in training neural-network language model for ontology population

P Lomov, M Malozemova, M Shishaev - Data Science and Intelligent …, 2021 - Springer
data augmentation, as well as approaches for solving the problem of nested named entities
extraction… For example, Sun and Jiang [8] propose an algorithm for correcting misspelled …

[HTML][HTML] Asr error correction with augmented transformer for entity retrieval

H Wang, S Dong, Y Liu, J Logan, A Agrawal, Y Liu - 2020 - amazon.science
… a novel augmented variant of the Transformer model that encodes both the word and phoneme
sequence of an entity, … named entities. We evaluate our method on both the ASR error …

Rethinking generalization of neural models: A named entity recognition case study

J Fu, P Liu, Q Zhang - Proceedings of the AAAI Conference on Artificial …, 2020 - ojs.aaai.org
… the generalization behavior from multiple novel angles, which con… Finally, we corrected 65
sentences in the test set, and 14 … multiple training sets for data augmentation, the order of the …