Downloads provided by UsageCounts
Dans cet article, nous présentons un ensemble de données et une évaluation de base pour l'extraction d'événements épidémiques multilingues. Nous expérimentons avec un ensemble de données d'actualités multilingues que nous annotons au niveau des jetons, un schéma de balisage commun utilisé dans les systèmes d'extraction d'événements. Nous abordons la tâche d'extraire les événements épidémiques en détectant d'abord les documents pertinents à partir d'une grande collection de reportages. Ensuite, l'extraction des événements (noms et emplacements des maladies) est effectuée sur les documents pertinents détectés. Des expériences préliminaires avec l'ensemble des données et des documents pertinents sur la vérité du terrain ont montré des résultats prometteurs, tout en établissant une base de référence plus solide pour l'extraction des événements épidémiologiques.
En este documento, presentamos un conjunto de datos y una evaluación de referencia para la extracción multilingüe de eventos epidémicos. Experimentamos con un conjunto de datos de noticias multilingües que anotamos a nivel de token, un esquema de etiquetado común utilizado en los sistemas de extracción de eventos. Abordamos la tarea de extraer eventos epidémicos detectando primero los documentos relevantes de una gran colección de informes de noticias. Luego, se realiza la extracción del evento (nombres y ubicaciones de la enfermedad) en los documentos relevantes detectados. Los experimentos preliminares con todo el conjunto de datos y con documentos relevantes sobre el terreno mostraron resultados prometedores, al tiempo que establecieron una línea de base más sólida para la extracción de eventos epidemiológicos.
In this paper, we present a dataset and a baseline evaluation for multilingual epidemic event extraction. We experiment with a multilingual news dataset which we annotate at the token level, a common tagging scheme utilized in event extraction systems. We approach the task of extracting epidemic events by first detecting the relevant documents from a large collection of news reports. Then, event extraction (disease names and locations) is performed on the detected relevant documents. Preliminary experiments with the entire dataset and with ground-truth relevant documents showed promising results, while also establishing a stronger baseline for epidemiological event extraction.
في هذه الورقة، نقدم مجموعة بيانات وتقييمًا أساسيًا لاستخراج الأحداث الوبائية متعددة اللغات. نقوم بتجربة مجموعة بيانات إخبارية متعددة اللغات نقوم بتعليقها على مستوى الرمز المميز، وهو نظام وسم شائع يستخدم في أنظمة استخراج الأحداث. نحن نتعامل مع مهمة استخراج الأحداث الوبائية من خلال الكشف أولاً عن الوثائق ذات الصلة من مجموعة كبيرة من التقارير الإخبارية. بعد ذلك، يتم استخراج الأحداث (أسماء الأمراض ومواقعها) على الوثائق ذات الصلة المكتشفة. أظهرت التجارب الأولية مع مجموعة البيانات بأكملها ومع الوثائق ذات الصلة بالحقيقة الأرضية نتائج واعدة، مع إنشاء خط أساس أقوى لاستخراج الأحداث الوبائية.
Digital Epidemiology and Disease Surveillance, Artificial intelligence, Epidemiology, Multilingualism, Extraction, Ground truth, Oceanography, Mathematical analysis, Quantum mechanics, Systems engineering, Task (project management), Engineering, Artificial Intelligence, Extraction (chemistry), Computer security, Health Sciences, FOS: Mathematics, Information retrieval, Sequence labeling, Event (particle physics), Natural Language Processing, Scheme (mathematics), Chromatography, Topic Modeling, Baseline (sea), Natural language processing, Physics, Epidemiological surveillance, Epidemiological Surveillance, Multilingualism, Sequence Labeling., Geology, FOS: Earth and related environmental sciences, Named Entity Recognition, Computer science, Automatic Keyword Extraction from Textual Data, Epidemic Detection, Chemistry, Security token, Computer Science, Physical Sciences, Medicine, Mathematics
Digital Epidemiology and Disease Surveillance, Artificial intelligence, Epidemiology, Multilingualism, Extraction, Ground truth, Oceanography, Mathematical analysis, Quantum mechanics, Systems engineering, Task (project management), Engineering, Artificial Intelligence, Extraction (chemistry), Computer security, Health Sciences, FOS: Mathematics, Information retrieval, Sequence labeling, Event (particle physics), Natural Language Processing, Scheme (mathematics), Chromatography, Topic Modeling, Baseline (sea), Natural language processing, Physics, Epidemiological surveillance, Epidemiological Surveillance, Multilingualism, Sequence Labeling., Geology, FOS: Earth and related environmental sciences, Named Entity Recognition, Computer science, Automatic Keyword Extraction from Textual Data, Epidemic Detection, Chemistry, Security token, Computer Science, Physical Sciences, Medicine, Mathematics
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 2 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
| views | 11 | |
| downloads | 16 |

Views provided by UsageCounts
Downloads provided by UsageCounts