Accountable and Explainable Methods for Complex Reasoning over Text

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 mo...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Atanasova, Pepa (مؤلف)
مؤلف مشترك: SpringerLink (Online service)
التنسيق: الكتروني كتاب الكتروني
اللغة:الإنجليزية
منشور في: Cham : Springer Nature Switzerland : Imprint: Springer, 2024.
الطبعة:1st ed. 2024.
الموضوعات:
الوصول للمادة أونلاين:https://doi.org/10.1007/978-3-031-51518-7
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

MARC

LEADER 00000nam a22000005i 4500
001 978-3-031-51518-7
003 DE-He213
005 20260810160453.0
007 cr nn 008mamaa
008 240405s2024 sz | o |||| 0|eng d
020 |a 9783031515187  |9 978-3-031-51518-7 
024 7 |a 10.1007/978-3-031-51518-7  |2 doi 
050 4 |a QA76.9.N38 
072 7 |a UYQL  |2 bicssc 
072 7 |a COM073000  |2 bisacsh 
072 7 |a UYQL  |2 thema 
082 0 4 |a 006.35  |2 23 
100 1 |a Atanasova, Pepa.  |e author.  |4 aut  |4 http://id.loc.gov/vocabulary/relators/aut 
245 1 0 |a Accountable and Explainable Methods for Complex Reasoning over Text  |h [electronic resource] /  |c by Pepa Atanasova. 
250 |a 1st ed. 2024. 
264 1 |a Cham :  |b Springer Nature Switzerland :  |b Imprint: Springer,  |c 2024. 
300 |a 1 online resource (XVIII, 199 p. 24 illus.).  |b 24 illus. in color. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
341 0 |b Table of contents navigation  |2 onix 
341 0 |b Single logical reading order  |2 onix 
341 0 |b Short alternative textual descriptions  |2 onix 
341 0 |b Use of color is not sole means of conveying information  |2 onix 
341 0 |b Use of high contrast between text and background color  |2 onix 
341 0 |b Next / Previous structural navigation  |2 onix 
341 0 |b All non-decorative content supports reading without sight  |2 onix 
347 |a text file  |b PDF  |2 rda 
505 0 |a 1. Executive Summary -- Part I: Accountability for Complex Reasoning Tasks over Text -- 2. Fact Checking with Insufficient Evidence -- 3. Generating Label Cohesive and Well-Formed Adversarial Claims -- Part II: Explainability for Complex Reasoning Tasks over Text -- 4. Generating Fact Checking Explanations -- 5. Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing -- 6. Multi-Hop Fact Checking of Political Claims -- Part III: Diagnostic Explainability Methods -- 7. A Diagnostic Study of Explainability Techniques for Text Classification -- 8. Diagnostics-Guided Explanation Generation -- 9. Recent Developments on Accountability and Explainability for Complex Reasoning Tasks. 
520 |a 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 of Copenhagen, 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. 
532 8 |a Accessibility summary: This PDF does not fully comply with PDF/UA standards, but does feature limited screen reader support, described non-text content (images, graphs), bookmarks for easy navigation and searchable, selectable text. Users of assistive technologies may experience difficulty navigating or interpreting content in this document. We recognize the importance of accessibility, and we welcome queries about accessibility for any of our products. If you have a question or an access need, please get in touch with us at accessibilitysupport@springernature.com. 
532 8 |a No reading system accessibility options actively disabled 
532 8 |a Publisher contact for further accessibility information: accessibilitysupport@springernature.com 
588 |a Print version record. 
650 0 |a Natural language processing (Computer science). 
650 0 |a Information storage and retrieval systems. 
650 0 |a Machine learning. 
650 1 4 |a Natural Language Processing (NLP). 
650 2 4 |a Information Storage and Retrieval. 
650 2 4 |a Machine Learning. 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer Nature eBook 
776 0 8 |i Printed edition:  |z 9783031515170 
776 0 8 |i Printed edition:  |z 9783031515194 
856 4 0 |u https://doi.org/10.1007/978-3-031-51518-7 
912 |a ZDB-2-SCS 
912 |a ZDB-2-SXCS 
950 |a Computer Science (SpringerNature-11645) 
950 |a Computer Science (R0) (SpringerNature-43710)