Scalable Detection of Salient Entities in News Articles

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Asgarieh, Eliyar, Thadani, Kapil, O'Hare, Neil
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913371435040768
author Asgarieh, Eliyar
Thadani, Kapil
O'Hare, Neil
author_facet Asgarieh, Eliyar
Thadani, Kapil
O'Hare, Neil
contents News articles typically mention numerous entities, a large fraction of which are tangential to the story. Detecting the salience of entities in articles is thus important to applications such as news search, analysis and summarization. In this work, we explore new approaches for efficient and effective salient entity detection by fine-tuning pretrained transformer models with classification heads that use entity tags or contextualized entity representations directly. Experiments show that these straightforward techniques dramatically outperform prior work across datasets with varying sizes and salience definitions. We also study knowledge distillation techniques to effectively reduce the computational cost of these models without affecting their accuracy. Finally, we conduct extensive analyses and ablation experiments to characterize the behavior of the proposed models.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20461
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scalable Detection of Salient Entities in News Articles
Asgarieh, Eliyar
Thadani, Kapil
O'Hare, Neil
Computation and Language
News articles typically mention numerous entities, a large fraction of which are tangential to the story. Detecting the salience of entities in articles is thus important to applications such as news search, analysis and summarization. In this work, we explore new approaches for efficient and effective salient entity detection by fine-tuning pretrained transformer models with classification heads that use entity tags or contextualized entity representations directly. Experiments show that these straightforward techniques dramatically outperform prior work across datasets with varying sizes and salience definitions. We also study knowledge distillation techniques to effectively reduce the computational cost of these models without affecting their accuracy. Finally, we conduct extensive analyses and ablation experiments to characterize the behavior of the proposed models.
title Scalable Detection of Salient Entities in News Articles
topic Computation and Language
url https://arxiv.org/abs/2405.20461