Téléchargez le livre : Accountable and Explainable Methods for Complex Reasoning over Text

Accountable and Explainable Methods for Complex Reasoning over Text



de

Éditeur :

Springer


Paru le : 2024-04-05



eBook Téléchargement , DRM LCP 🛈 DRM Adobe 🛈
Lecture en ligne (streaming)
89,66 €
Téléchargement immédiat
Dès validation de votre commande
Ajouter à ma liste d'envies
Image Louise Reader présentation

Louise Reader

Lisez ce titre sur l'application Louise Reader.

badge apple Application Louise Reader
badge Android Application Louise Reader
Description

This thesis presents research that expands the collective knowledge in the areas of accountability and transparency of machine learning (ML) models developed for complex reasoning tasks over text. In particular, the presented results facilitate the analysis of the reasons behind the outputs of ML models and assist in detecting and correcting for potential harms. It presents two new methods for accountable ML models; advances the state of the art with methods generating textual explanations that are further improved to be fluent, easy to read, and to contain logically connected multi-chain arguments; and makes substantial contributions in the area of diagnostics for explainability approaches. All results are empirically tested on complex reasoning tasks over text, including fact checking, question answering, and natural language inference.
This book is a revised version of the PhD dissertation written by the author to receive her PhD from the Faculty of Science, University ofCopenhagen, Denmark. In 2023, it won the Informatics Europe Best Dissertation Award, granted to the most outstanding European PhD thesis in the field of computer science.
Pages
199 pages
Collection
n.c
Parution
2024-04-05
Marque
Springer
EAN papier
9783031515170
EAN PDF
9783031515187
Informations sur l'ebook
Nombre pages copiables
1
Nombre pages imprimables
19
Taille du fichier
27392 Ko
Ce livre est accessible aux handicaps Voir les informations sur l'accessibilité
Prix
89,66 €
EAN EPUB
9783031515187
Informations sur l'ebook
Nombre pages copiables
1
Nombre pages imprimables
19
Taille du fichier
23726 Ko
Ce livre est accessible aux handicaps Voir les informations sur l'accessibilité
Prix
89,66 €

Pepa Atanasova is a postdoctoral researcher at the University of Copenhagen. She has received her PhD degree at the University of Copenhagen receiving the Best Dissertation Award of Informatics Europe in 2023. Her current research focuses on explainability for machine learning models, encompassing natural language explanations, post-hoc explainability methods, and adversarial attacks as well as the principled evaluation of existing explainability techniques.


Suggestions personnalisées