Dealing with negative samples with multi-task learning on span-based joint entity-relation extraction

• URL: http://arxiv.org/abs/2309.09713v1
• Date: Mon, 18 Sep 2023 12:28:46 GMT
• Title: Dealing with negative samples with multi-task learning on span-based joint entity-relation extraction
• Authors: Chenguang Xue and Jiamin Lu
• Abstract summary: Recent span-based joint extraction models have demonstrated significant advantages in both entity recognition and relation extraction. This paper introduces a span-based multitask entity-relation joint extraction model.
• Score: 0.7252027234425334
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent span-based joint extraction models have demonstrated significant advantages in both entity recognition and relation extraction. These models treat text spans as candidate entities, and span pairs as candidate relationship tuples, achieving state-of-the-art results on datasets like ADE. However, these models encounter a significant number of non-entity spans or irrelevant span pairs during the tasks, impairing model performance significantly. To address this issue, this paper introduces a span-based multitask entity-relation joint extraction model. This approach employs the multitask learning to alleviate the impact of negative samples on entity and relation classifiers. Additionally, we leverage the Intersection over Union(IoU) concept to introduce the positional information into the entity classifier, achieving a span boundary detection. Furthermore, by incorporating the entity Logits predicted by the entity classifier into the embedded representation of entity pairs, the semantic input for the relation classifier is enriched. Experimental results demonstrate that our proposed SpERT.MT model can effectively mitigate the adverse effects of excessive negative samples on the model performance. Furthermore, the model demonstrated commendable F1 scores of 73.61\%, 53.72\%, and 83.72\% on three widely employed public datasets, namely CoNLL04, SciERC, and ADE, respectively.

Related papers

• Joint Extraction of Uyghur Medicine Knowledge with Edge Computing [1.4223082738595538]
  CoEx-Bert is a joint extraction model with parameter sharing in edge computing. It achieves accuracy, recall, and F1 scores of 90.65%, 92.45%, and 91.54%, respectively, in the Uyghur traditional medical dataset.
  arXiv  Detail & Related papers  (2024-01-13T08:27:24Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning [18.45898471459533]
  Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. This paper proposes a novel approach to address spurious correlations during fine-tuning for a given domain of interest.
  arXiv  Detail & Related papers  (2023-04-08T05:20:33Z)
• Unified Visual Relationship Detection with Vision and Language Models [89.77838890788638]
  This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. We propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model.
  arXiv  Detail & Related papers  (2023-03-16T00:06:28Z)
• Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks [54.306234256074255]
  We identify the issue of tokenization inconsistency that is commonly neglected in training generative models. This issue damages the extractive nature of these tasks after the input and output are tokenized inconsistently. We show that, with consistent tokenization, the model performs better in both in-domain and out-of-domain datasets.
  arXiv  Detail & Related papers  (2022-12-19T23:33:21Z)
• A Two-Phase Paradigm for Joint Entity-Relation Extraction [11.92606118894611]
  We propose a two-phase paradigm for the span-based joint entity and relation extraction. The two-phase paradigm involves classifying the entities and relations in the first phase, and predicting the types of these entities and relations in the second phase. Experimental results on several datasets demonstrate that the spanbased joint extraction model augmented with the two-phase paradigm and the global features consistently outperforms previous state-of-the-art span-based models for the joint extraction task.
  arXiv  Detail & Related papers  (2022-08-18T06:40:25Z)
• On Modality Bias Recognition and Reduction [70.69194431713825]
  We study the modality bias problem in the context of multi-modal classification. We propose a plug-and-play loss function method, whereby the feature space for each label is adaptively learned. Our method yields remarkable performance improvements compared with the baselines.
  arXiv  Detail & Related papers  (2022-02-25T13:47:09Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)
• Combining Feature and Instance Attribution to Detect Artifacts [62.63504976810927]
  We propose methods to facilitate identification of training data artifacts. We show that this proposed training-feature attribution approach can be used to uncover artifacts in training data. We execute a small user study to evaluate whether these methods are useful to NLP researchers in practice.
  arXiv  Detail & Related papers  (2021-07-01T09:26:13Z)
• An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning [2.111790330664657]
  We present a joint model for entity-level relation extraction from documents. We achieve state-of-the-art relation extraction results on the DocRED dataset. Our experimental results suggest that a joint approach is on par with task-specific learning, though more efficient due to shared parameters and training steps.
  arXiv  Detail & Related papers  (2021-02-11T12:49:39Z)
• Joint Extraction of Entity and Relation with Information Redundancy Elimination [0.0]
  We propose a joint extraction model to solve the problem of redundant information and overlapping relations of the entity and relation extraction model. This model can directly extract multiple pairs of related entities without generating unrelated information. We also propose a recurrent neural network named-LSTM that enhances the ability of recurrent units to model sentences.
  arXiv  Detail & Related papers  (2020-11-27T05:47:26Z)

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.