S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition

• URL: http://arxiv.org/abs/2310.18944v1
• Date: Sun, 29 Oct 2023 09:09:10 GMT
• Title: S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition
• Authors: Yongxiu Xu and Heyan Huang and Yue Hu
• Abstract summary: We propose a novel Sequence-to-Forest generation paradigm, S2F-NER, which can directly extract entities in sentence via a Forest decoder. Specifically, our model generate each path of each tree in forest autoregressively, where the maximum depth of each tree is three. Based on this novel paradigm, our model can elegantly mitigate the exposure bias problem and keep the simplicity of Seq2Seq.
• Score: 47.714230389689064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Named Entity Recognition (NER) remains challenging due to the complex entities, like nested, overlapping, and discontinuous entities. Existing approaches, such as sequence-to-sequence (Seq2Seq) generation and span-based classification, have shown impressive performance on various NER subtasks, but they are difficult to scale to datasets with longer input text because of either exposure bias issue or inefficient computation. In this paper, we propose a novel Sequence-to-Forest generation paradigm, S2F-NER, which can directly extract entities in sentence via a Forest decoder that decode multiple entities in parallel rather than sequentially. Specifically, our model generate each path of each tree in forest autoregressively, where the maximum depth of each tree is three (which is the shortest feasible length for complex NER and is far smaller than the decoding length of Seq2Seq). Based on this novel paradigm, our model can elegantly mitigates the exposure bias problem and keep the simplicity of Seq2Seq. Experimental results show that our model significantly outperforms the baselines on three discontinuous NER datasets and on two nested NER datasets, especially for discontinuous entity recognition.

Related papers

• Single-Stage Visual Relationship Learning using Conditional Queries [60.90880759475021]
  TraCQ is a new formulation for scene graph generation that avoids the multi-task learning problem and the entity pair distribution. We employ a DETR-based encoder-decoder conditional queries to significantly reduce the entity label space as well. Experimental results show that TraCQ not only outperforms existing single-stage scene graph generation methods, it also beats many state-of-the-art two-stage methods on the Visual Genome dataset.
  arXiv  Detail & Related papers  (2023-06-09T06:02:01Z)
• Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition [52.46740830977898]
  We propose a novel seq2seq model named GPRL, which formulates the nested NER task as an entity triplet sequence generation process. Experiments on three nested NER datasets demonstrate that GPRL outperforms previous nested NER models.
  arXiv  Detail & Related papers  (2023-05-12T05:55:34Z)
• Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition [35.44123819012004]
  Named entity recognition (NER) is an important research problem in natural language processing. This paper proposes a multi-task Transformer, which incorporates an entity boundary detection task into the named entity recognition task.
  arXiv  Detail & Related papers  (2023-03-20T05:11:22Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition [55.080101447586635]
  We propose using Conal Neural Network (CNN) to model spatial relations in the score matrix. Our model surpasses several recently proposed methods with the same pre-trained encoders.
  arXiv  Detail & Related papers  (2022-08-09T04:33:46Z)
• A Sequence-to-Set Network for Nested Named Entity Recognition [38.05786148160635]
  We propose a novel sequence-to-set neural network for nested NER. We use a non-autoregressive decoder to predict the final set of entities in one pass. Experimental results show that our proposed model achieves state-of-the-art on three nested NER corpora.
  arXiv  Detail & Related papers  (2021-05-19T03:10:04Z)
• Nested Named Entity Recognition with Partially-Observed TreeCRFs [23.992944831013013]
  We view nested NER as constituency parsing with partially-observed trees and model it with partially-observed TreeCRFs. Our approach achieves the state-of-the-art (SOTA) F1 scores on the ACE2004, ACE2005 dataset, and shows comparable performance to SOTA models on the GENIA dataset.
  arXiv  Detail & Related papers  (2020-12-15T18:20:36Z)
• Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction [57.22929457171352]
  Joint entity and relation extraction aims to extract relation triplets from plain text directly. We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias.
  arXiv  Detail & Related papers  (2020-09-16T06:53:34Z)

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.