From BERT to T5: A Study of Named Entity Recognition

• URL: http://arxiv.org/abs/2605.18462v1
• Date: Mon, 18 May 2026 14:23:35 GMT
• Title: From BERT to T5: A Study of Named Entity Recognition
• Abstract summary: This report focuses on implementing the NER task on finetuning two pretrained models.<n>BERT is applied a weighted cross-entropy for training loss, and T5 is fine-tuned with two validation strategies.<n>The related analysis provides valuable insights into common errors in BERT and the two models' performance.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Named entity recognition (NER) has been one of the essential preliminary steps in modern NLP applications. This report focuses on implementing the NER task on finetuning two pretrained models: (i) an encoder-only model (BERT) with a simple classification head, and (ii) a sequence-to-sequence model (T5) with few-shot prompts. Under the original 7-class tag and 3-class simplified tag schemes, BERT is applied a weighted cross-entropy for training loss, and T5 is fine-tuned with two validation strategies. It also conducted an ablation study with different hyperparameters. Moreover, the related analysis provides valuable insights into common errors in BERT and the two models' performance. Based on a bunch of performance metrics, this report aims to compare the above two architectures and explore their abilities in the sequence labelling task, laying the groundwork for further practical use cases.

Related papers

• NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training [6.030518150035875]
  This paper introduces a two-stage alignment strategy for EEG foundation models.<n>First, we propose NeuroTTT: a domain-specific self-supervised fine-tuning paradigm.<n>Second, we perform self-supervised test-time training on individual unlabeled test samples.<n>Our approach is the first to unify domain-tuned self-supervision with test-time training in large-scale EEG foundation models.
  arXiv  Detail & Related papers  (2025-09-30T14:14:46Z)
• Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Model [33.446533426654995]
  We design a heterogeneous knowledge-infused framework to strengthen BERT-based CSC models. We propose a novel form of n-gram-based layerwise self-attention to generate a multilayer representation. Experimental results show that our proposed framework yields a stable performance boost over four strong baseline models.
  arXiv  Detail & Related papers  (2023-12-27T16:11:07Z)
• Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition [23.69922938823477]
  We propose a method called task Relation Distillation and Prototypical pseudo label (RDP) for INER. Our method achieves significant improvements over the previous state-of-the-art methods, with an average increase of 6.08% in Micro F1 score and 7.71% in Macro F1 score.
  arXiv  Detail & Related papers  (2023-08-17T05:36:56Z)
• Enhancing Few-shot NER with Prompt Ordering based Data Augmentation [59.69108119752584]
  We propose a Prompt Ordering based Data Augmentation (PODA) method to improve the training of unified autoregressive generation frameworks. Experimental results on three public NER datasets and further analyses demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-05-19T16:25:43Z)
• A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition [24.916377682689955]
  Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. We propose a Prototypical Semantic Decoupling method via joint Contrastive learning (PSDC) for few-shot NER. Experimental results on two few-shot NER benchmarks demonstrate that PSDC consistently outperforms the previous SOTA methods in terms of overall performance.
  arXiv  Detail & Related papers  (2023-02-27T09:20:00Z)
• Pack Together: Entity and Relation Extraction with Levitated Marker [61.232174424421025]
  We propose a novel span representation approach, named Packed Levitated Markers, to consider the dependencies between the spans (pairs) by strategically packing the markers in the encoder. Our experiments show that our model with packed levitated markers outperforms the sequence labeling model by 0.4%-1.9% F1 on three flat NER tasks, and beats the token concat model on six NER benchmarks.
  arXiv  Detail & Related papers  (2021-09-13T15:38:13Z)
• Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation [58.64720318755764]
  Semi-Supervised Learning (SSL) has seen success in many application domains, but this success often hinges on the availability of task-specific unlabeled data. Knowledge distillation (KD) has enabled compressing deep networks and ensembles, achieving the best results when distilling knowledge on fresh task-specific unlabeled examples. We present a general framework called "generate, annotate, and learn (GAL)" that uses unconditional generative models to synthesize in-domain unlabeled data.
  arXiv  Detail & Related papers  (2021-06-11T05:01:24Z)
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing [51.81533991497547]
  Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries. We present X2 compared a transferable Cross-lingual and Cross-domain for TCSP. We propose to predict flattened intents and slots representations separately and cast both prediction tasks into sequence labeling problems.
  arXiv  Detail & Related papers  (2021-06-07T16:40:05Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.