Back to all available

Global-Attn-GateNER: Unified entity recognition based on global attention and dynamic gateway

artificial-intelligence
computer-education
data-mining-and-machine-learning
natural-language-and-speech

Abstract

Unified modeling poses a significant challenge for Named Entity Recognition (NER), for which efficiently capturing semantic and feature fusion remains critical. The W2 NER framework, based on word-word relationship classification, offers a unified approach to NER through two-dimensional word grid modeling. However, this framework suffers from insufficient context awareness and rigid feature interactions. To overcome these limitations, this study proposes a phased enhancement strategy consisting of several steps:(1) a global self attention mechanism strengthens boundary semantic representations; (2) then, a restructured hierarchical perturbation strategy mitigates over-regularization in the dual-affine module; and (3) a dynamically gated fusion network achieves adaptive aggregation of structured features and contextual representations at the word-pair granularity. Extensive experiments across eight benchmark datasets, which cover flat, overlapping, and discontinuous NER (four Chinese and four English datasets), demonstrate this proposed model’s state-of-the-art performance, thereby propelling unified NER to new frontiers.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].