LEADER 03585nam a22004815i 4500001    99130574249306421
005    20240406124731.0
006    m     o  d |
007    cr |||||||||||
008    240405s2024    sz |    o    |||| 0|eng d
020    3-031-51518-8
024 7  10.1007/978-3-031-51518-7 |2doi
035    (CKB)31403749500041
035    (MiAaPQ)EBC31267110
035    (Au-PeEL)EBL31267110
035    (MiAaPQ)EBC31253958
035    (Au-PeEL)EBL31253958
035    (DE-He213)978-3-031-51518-7
035    (EXLCZ)9931403749500041
040    MiAaPQ |beng |erda |epn |cMiAaPQ |dMiAaPQ
050  4 Q325.5 |b.A836 2024
072  7 UYQL |2bicssc
072  7 COM073000 |2bisacsh
072  7 UYQL |2thema
082 0  006.31 |223
100 1  Atanasova, Pepa, |eauthor.
245 10 Accountable and Explainable Methods for Complex Reasoning over Text / |cby Pepa Atanasova.
250    1st ed. 2024.
264  1 Cham : |bSpringer Nature Switzerland : |bImprint: Springer, |c2024.
300    1 online resource (208 pages)
336    text |btxt |2rdacontent
337    computer |bc |2rdamedia
338    online resource |bcr |2rdacarrier
505 0  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    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.
650  0 Natural language processing (Computer science).
650  0 Information storage and retrieval systems.
650  0 Machine learning.
650 14 Natural Language Processing (NLP).
650 24 Information Storage and Retrieval.
650 24 Machine Learning.
776     |z3-031-51517-X
906    BOOK