Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ https://www.aclweb.o...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
https://www.aclweb.org/antholo...
Article
License: CC BY
Data sources: UnpayWall
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
https://doi.org/10.18653/v1/20...
Article . 2020 . Peer-reviewed
Data sources: Crossref
https://dx.doi.org/10.60692/0a...
Other literature type . 2020
Data sources: Datacite
https://dx.doi.org/10.60692/s1...
Other literature type . 2020
Data sources: Datacite
DBLP
Conference object
Data sources: DBLP
versions View all 7 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Automatic Discovery of Heterogeneous Machine Learning Pipelines: An Application to Natural Language Processing

الاكتشاف التلقائي لخطوط أنابيب التعلم الآلي غير المتجانسة: تطبيق لمعالجة اللغة الطبيعية
Authors: Suilán Estévez-Velarde; Yoan Gutiérrez; Andrés Montoyo; Yudivián Almeida-Cruz;

Automatic Discovery of Heterogeneous Machine Learning Pipelines: An Application to Natural Language Processing

Abstract

Cet article présente AutoGOAL, un système d'apprentissage automatique (AutoML) qui utilise des techniques hétérogènes. Contrairement aux approches AutoML existantes, notre contribution peut construire automatiquement des pipelines d'apprentissage automatique qui combinent des techniques et des algorithmes à partir de différents cadres, y compris des classificateurs peu profonds, des outils de traitement du langage naturel et des réseaux neuronaux. Nous définissons le problème d'optimisation AutoML hétérogène comme la recherche de la meilleure séquence d'algorithmes qui transforme des données d'entrée spécifiques en sortie souhaitée. Cela fournit une nouvelle approche théorique et pratique à AutoML. Notre proposition est évaluée expérimentalement dans divers problèmes d'apprentissage automatique et comparée à des approches alternatives, montrant qu'elle est compétitive avec d'autres alternatives AutoML dans des repères standard. En outre, elle peut être appliquée à de nouveaux scénarios, tels que plusieurs tâches NLP, où les alternatives existantes ne peuvent pas être directement déployées. Le système est disponible gratuitement et comprend une compatibilité intégrée avec un grand nombre de cadres d'apprentissage automatique populaires, ce qui rend notre approche utile pour résoudre des problèmes pratiques avec une facilité et un effort relatifs.

Este documento presenta AutoGOAL, un sistema para el aprendizaje automático de máquinas (AutoML) que utiliza técnicas heterogéneas. En contraste con los enfoques AutoML existentes, nuestra contribución puede construir automáticamente canalizaciones de aprendizaje automático que combinan técnicas y algoritmos de diferentes marcos, incluidos clasificadores superficiales, herramientas de procesamiento de lenguaje natural y redes neuronales. Definimos el problema de optimización de AutoML heterogéneo como la búsqueda de la mejor secuencia de algoritmos que transforma datos de entrada específicos en la salida deseada. Esto proporciona un enfoque teórico y práctico novedoso a AutoML. Nuestra propuesta se evalúa experimentalmente en diversos problemas de aprendizaje automático y se compara con enfoques alternativos, lo que demuestra que es competitivo con otras alternativas de AutoML en puntos de referencia estándar. Además, se puede aplicar a escenarios novedosos, como varias tareas de PNL, donde las alternativas existentes no se pueden implementar directamente. El sistema está disponible de forma gratuita e incluye compatibilidad incorporada con una gran cantidad de marcos de aprendizaje automático populares, lo que hace que nuestro enfoque sea útil para resolver problemas prácticos con relativa facilidad y esfuerzo.

This paper presents AutoGOAL, a system for automatic machine learning (AutoML) that uses heterogeneous techniques.In contrast with existing AutoML approaches, our contribution can automatically build machine learning pipelines that combine techniques and algorithms from different frameworks, including shallow classifiers, natural language processing tools, and neural networks.We define the heterogeneous AutoML optimization problem as the search for the best sequence of algorithms that transforms specific input data into the desired output.This provides a novel theoretical and practical approach to AutoML.Our proposal is experimentally evaluated in diverse machine learning problems and compared with alternative approaches, showing that it is competitive with other AutoML alternatives in standard benchmarks.Furthermore, it can be applied to novel scenarios, such as several NLP tasks, where existing alternatives cannot be directly deployed.The system is freely available and includes in-built compatibility with a large number of popular machine learning frameworks, which makes our approach useful for solving practical problems with relative ease and effort.

تقدم هذه الورقة AutoGOAL، وهو نظام للتعلم الآلي الآلي (AutoML) يستخدم تقنيات غير متجانسة. على النقيض من مناهج AutoML الحالية، يمكن لمساهمتنا أن تبني تلقائيًا خطوط أنابيب للتعلم الآلي تجمع بين التقنيات والخوارزميات من أطر مختلفة، بما في ذلك المصنفات الضحلة وأدوات معالجة اللغة الطبيعية والشبكات العصبية. نحدد مشكلة تحسين AutoML غير المتجانسة على أنها البحث عن أفضل تسلسل للخوارزميات التي تحول بيانات مدخلات محددة إلى المخرجات المطلوبة. يوفر هذا نهجًا نظريًا وعمليًا جديدًا لـ AutoML. يتم تقييم اقتراحنا تجريبيًا في مشاكل التعلم الآلي المتنوعة ومقارنته بالنهج البديلة، مما يدل على أنه قادر على المنافسة مع بدائل AutoML الأخرى في المعايير القياسية. علاوة على ذلك، يمكن تطبيقه على سيناريوهات جديدة، مثل العديد من مهام البرمجة اللغوية العصبية، حيث لا يمكن نشر البدائل الموجودة مباشرة. النظام متاح مجانًا ويتضمن توافقًا مدمجًا مع عدد كبير من أطر التعلم الآلي الشائعة، مما يجعل نهجنا مفيدًا لحل المشكلات العملية بسهولة وجهد نسبيًا.

Country
Spain
Keywords

Artificial intelligence, Hyperparameter Optimization, Natural language processing, FOS: Environmental engineering, Environmental engineering, AutoGOAL, Computer science, Learning with Noisy Labels in Machine Learning, Automated Machine Learning, Machine Translation, Engineering, Natural language, Artificial Intelligence, Meta-Learning, Machine learning, Lenguajes y Sistemas Informáticos, Computer Science, Physical Sciences, Pipeline transport, Active Learning in Machine Learning Research, Natural Language Processing, Robust Learning

  • BIP!
    Impact byBIP!
    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).
    4
    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.
    Top 10%
    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
Powered by OpenAIRE graph
Found an issue? Give us feedback
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).
BIP!Citations provided by BIP!
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.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
4
Top 10%
Average
Average
Green
hybrid