Enhancing Low-resource Fine-grained Named Entity Recognition by Leveraging Coarse-grained Datasets

• URL: http://arxiv.org/abs/2310.11715v2
• Date: Mon, 13 Nov 2023 13:18:58 GMT
• Title: Enhancing Low-resource Fine-grained Named Entity Recognition by Leveraging Coarse-grained Datasets
• Authors: Su Ah Lee, Seokjin Oh and Woohwan Jung
• Abstract summary: $K$-shot learning techniques can be applied, but their performance tends to saturate when the number of annotations exceeds several tens of labels. We propose a fine-grained NER model with a Fine-to-Coarse(F2C) mapping matrix to leverage the hierarchical structure explicitly. Our method outperforms both $K$-shot learning and supervised learning methods when dealing with a small number of fine-grained annotations.
• Score: 1.5500145658862499
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Named Entity Recognition (NER) frequently suffers from the problem of insufficient labeled data, particularly in fine-grained NER scenarios. Although $K$-shot learning techniques can be applied, their performance tends to saturate when the number of annotations exceeds several tens of labels. To overcome this problem, we utilize existing coarse-grained datasets that offer a large number of annotations. A straightforward approach to address this problem is pre-finetuning, which employs coarse-grained data for representation learning. However, it cannot directly utilize the relationships between fine-grained and coarse-grained entities, although a fine-grained entity type is likely to be a subcategory of a coarse-grained entity type. We propose a fine-grained NER model with a Fine-to-Coarse(F2C) mapping matrix to leverage the hierarchical structure explicitly. In addition, we present an inconsistency filtering method to eliminate coarse-grained entities that are inconsistent with fine-grained entity types to avoid performance degradation. Our experimental results show that our method outperforms both $K$-shot learning and supervised learning methods when dealing with a small number of fine-grained annotations.

Related papers

• Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains [51.02035914828596]
  We study the task of seed-guided fine-grained entity typing in science and engineering domains. We propose SEType which first enriches the weak supervision by finding more entities for each seen type from an unlabeled corpus. It then matches the enriched entities to unlabeled text to get pseudo-labeled samples and trains a textual entailment model that can make inferences for both seen and unseen types.
  arXiv  Detail & Related papers  (2024-01-23T22:36:03Z)
• Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances [55.37242480995541]
  We propose to denoise noisy NER data with guidance from a small set of clean instances. Along with the main NER model we train a discriminator model and use its outputs to recalibrate the sample weights. Results on public crowdsourcing and distant supervision datasets show that the proposed method can consistently improve performance with a small guidance set.
  arXiv  Detail & Related papers  (2023-10-25T17:23:37Z)
• Continual Named Entity Recognition without Catastrophic Forgetting [37.316700599440935]
  We introduce a pooled feature distillation loss that skillfully navigates the trade-off between retaining knowledge of old entity types and acquiring new ones. We develop a confidence-based pseudo-labeling for the non-entity type. We suggest an adaptive re-weighting type-balanced learning strategy to handle the issue of biased type distribution.
  arXiv  Detail & Related papers  (2023-10-23T03:45:30Z)
• MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition [36.868805760086886]
  This dataset aims to tackle the following practical challenges in NER: (i) effective handling of fine-grained classes that include complex entities like movie titles, and (ii) performance degradation due to noise generated from typing mistakes or OCR errors. The dataset is compiled from open resources like Wikipedia and Wikidata, and is publicly available.
  arXiv  Detail & Related papers  (2023-10-20T01:14:46Z)
• PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning [24.29409958504209]
  We propose PIE, a textbfparameter and textbfinference textbfefficient solution. Inspired from tensor decomposition methods, we find that decompose entity embedding matrix into low rank matrices can reduce more than half of the parameters. To accelerate model inference, we propose a self-supervised auxiliary task, which can be seen as fine-grained entity typing.
  arXiv  Detail & Related papers  (2022-04-29T09:06:56Z)
• Learning with Noisy Labels by Targeted Relabeling [52.0329205268734]
  Crowdsourcing platforms are often used to collect datasets for training deep neural networks. We propose an approach which reserves a fraction of annotations to explicitly relabel highly probable labeling errors.
  arXiv  Detail & Related papers  (2021-10-15T20:37:29Z)
• Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition [9.809157050048375]
  We propose a two-stage entity identifier for named entity recognition. First, we generate span proposals by filtering and boundary regression on the seed spans to locate the entities, and then label the boundary-adjusted span proposals with the corresponding categories. Our method effectively utilizes the boundary information of entities and partially matched spans during training.
  arXiv  Detail & Related papers  (2021-05-14T12:52:34Z)
• Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition [47.273602658066196]
  In many scenarios, named entity recognition models severely suffer from unlabeled entity problem. We propose a general approach, which can almost eliminate the misguidance brought by unlabeled entities. Our model is robust to unlabeled entity problem and surpasses prior baselines.
  arXiv  Detail & Related papers  (2020-12-10T02:53:59Z)
• Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning [80.20302993614594]
  We provide a statistical analysis to overcome drawbacks of Laplacian regularization. We unveil a large body of spectral filtering methods that exhibit desirable behaviors. We provide realistic computational guidelines in order to make our method usable with large amounts of data.
  arXiv  Detail & Related papers  (2020-09-09T14:28:54Z)
• Temporal Calibrated Regularization for Robust Noisy Label Learning [60.90967240168525]
  Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation quality. We propose a Temporal Calibrated Regularization (TCR) in which we utilize the original labels and the predictions in the previous epoch together.
  arXiv  Detail & Related papers  (2020-07-01T04:48:49Z)

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.