End-to-End Dialog Neural Coreference Resolution: Balancing Efficiency and Accuracy in Large-Scale Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dong, Zhang, deng, Songhang, Wang, Mingbang, Dai, Le, Li, Jiyuan, Liu, Xingzu, Nong, Ruilin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917980653223936
author Dong, Zhang
deng, Songhang
Wang, Mingbang
Dai, Le
Li, Jiyuan
Liu, Xingzu
Nong, Ruilin
author_facet Dong, Zhang
deng, Songhang
Wang, Mingbang
Dai, Le
Li, Jiyuan
Liu, Xingzu
Nong, Ruilin
contents Large-scale coreference resolution presents a significant challenge in natural language processing, necessitating a balance between efficiency and accuracy. In response to this challenge, we introduce an End-to-End Neural Coreference Resolution system tailored for large-scale applications. Our system efficiently identifies and resolves coreference links in text, ensuring minimal computational overhead without compromising on performance. By utilizing advanced neural network architectures, we incorporate various contextual embeddings and attention mechanisms, which enhance the quality of predictions for coreference pairs. Furthermore, we apply optimization strategies to accelerate processing speeds, making the system suitable for real-world deployment. Extensive evaluations conducted on benchmark datasets demonstrate that our model achieves improved accuracy compared to existing approaches, while effectively maintaining rapid inference times. Rigorous testing confirms the ability of our system to deliver precise coreference resolutions efficiently, thereby establishing a benchmark for future advancements in this field.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05824
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle End-to-End Dialog Neural Coreference Resolution: Balancing Efficiency and Accuracy in Large-Scale Systems
Dong, Zhang
deng, Songhang
Wang, Mingbang
Dai, Le
Li, Jiyuan
Liu, Xingzu
Nong, Ruilin
Computation and Language
Large-scale coreference resolution presents a significant challenge in natural language processing, necessitating a balance between efficiency and accuracy. In response to this challenge, we introduce an End-to-End Neural Coreference Resolution system tailored for large-scale applications. Our system efficiently identifies and resolves coreference links in text, ensuring minimal computational overhead without compromising on performance. By utilizing advanced neural network architectures, we incorporate various contextual embeddings and attention mechanisms, which enhance the quality of predictions for coreference pairs. Furthermore, we apply optimization strategies to accelerate processing speeds, making the system suitable for real-world deployment. Extensive evaluations conducted on benchmark datasets demonstrate that our model achieves improved accuracy compared to existing approaches, while effectively maintaining rapid inference times. Rigorous testing confirms the ability of our system to deliver precise coreference resolutions efficiently, thereby establishing a benchmark for future advancements in this field.
title End-to-End Dialog Neural Coreference Resolution: Balancing Efficiency and Accuracy in Large-Scale Systems
topic Computation and Language
url https://arxiv.org/abs/2504.05824