Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 12, 2026Scientific ReportsOpen Access

Amharic neural coreference resolution with multi-head attention and named entity recognition

View Full Paper
Ask AI
Bookmark
Share

Authors

YAYitayal AbateYAYaregal AssabieWMWolfgang Menzel

Discussion

Loading...

Member takes

Overview

Randomized trial investigates coreference resolution in Amharic, suggesting improved accuracy with advanced methods.

Key Points

  • The study aims to develop an effective coreference resolution system specifically for the Amharic language.
  • Integrated multi-head attention and named entity recognition in the neural model.
  • Utilized bidirectional long short-term memory and conditional random field for enhancing mention detection.
  • Followed a comprehensive model architecture including preprocessing, contextualization, and a dedicated coreference resolution layer.
  • The approach demonstrated competitive performance on a custom-built Amharic coreference dataset.
  • Improved coreference resolution was observed by combining multi-head attention with named entity recognition.

Cite This Study

Abate et al. (2026) studied this question.

synapsesocial.com/papers/6a5332484f7abc118adedd2dhttps://doi.org/10.1038/s41598-026-50661-5
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Transformer-based coreference resolution modeling for Amharic text2026
  2. 2Towards Neural Named Entity Recognition System in Tigrinya with Large-scale Dataset2024
  3. 3The Generalization Ability of Coreference Resolution Systems2026
  4. 4Integrating K+ Entities into Coreference Resolution on Biomedical Texts2024 · 1 citations
  5. 5Multi-head three-affine attention mechanism for nested named entity recognition2026