Related Experiment Videos
Amharic neural coreference resolution with multi-head attention and named entity recognition
Yitayal Abate1, Yaregal Assabie2, Wolfgang Menzel3
1Department of Computer Science, Addis Ababa University, Addis Ababa, Ethiopia. yitayal.abate@aau.edu.et.
Scientific Reports
|July 10, 2026
Summary
This study introduces a neural coreference resolution system for Amharic, a low-resource language. By integrating multi-head attention (MHA) and named entity recognition (NER), the system effectively identifies entities in text.
Area of Science:
- Natural Language Processing
- Computational Linguistics
- Low-Resource Language Technology
Background:
- Coreference resolution is vital for understanding text but challenging for morphologically rich, low-resource languages like Amharic.
- Existing Amharic NLP resources are limited, hindering the development of advanced coreference resolution systems.
- Neural network approaches offer potential but require careful adaptation to linguistic specificities.
Purpose of the Study:
- To develop and evaluate a novel neural coreference resolution system specifically designed for the Amharic language.
- To enhance mention detection and coreferent link identification by integrating multi-head attention and named entity recognition.
- To address the challenges posed by Amharic's morphological richness and limited annotated data.
Main Methods:
- A comprehensive neural architecture was proposed, including preprocessing, morphological analysis, contextualization, and span generation.
- Multi-head attention (MHA) was employed to capture complex contextual relationships between textual mentions.
- A named entity recognition (NER) module, using BiLSTM-CRF, was integrated to improve mention detection and candidate span generation.
Main Results:
- The proposed system demonstrated effective coreference resolution capabilities on a custom Amharic dataset.
- Experimental results showed competitive performance, validating the system's efficacy in a low-resource setting.
- The combination of MHA and NER modules yielded synergistic benefits, significantly improving resolution accuracy.
Conclusions:
- The developed neural coreference resolution system is effective for Amharic, a low-resource language.
- Integrating multi-head attention and named entity recognition is a promising strategy for improving coreference resolution in morphologically rich languages.
- This work contributes to advancing NLP capabilities for under-resourced languages.
Related Concept Videos
01:45ER Retrieval Pathway
In the secretory pathway, vesicles transport proteins from one cellular compartment to another in forward transport to deliver the protein to its correct location. Occasionally, misfolded proteins and incorrect proteins escape their original compartments, and a retrieval pathway is used to return the escaped proteins to their original compartment.
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
01:18Neural Control of Respiration
The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
01:25Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
01:21Association Areas of the Cortex
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
00:56Extraction: Advanced Methods
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is formed in...
01:29Aggregates Classification
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...