000 03641nam a22005055i 4500
001 978-3-031-51518-7
003 DE-He213
005 20240423130339.0
007 cr nn 008mamaa
008 240405s2024 sz | s |||| 0|eng d
020 _a9783031515187
_9978-3-031-51518-7
024 7 _a10.1007/978-3-031-51518-7
_2doi
050 4 _aQA76.9.N38
072 7 _aUYQL
_2bicssc
072 7 _aCOM073000
_2bisacsh
072 7 _aUYQL
_2thema
082 0 4 _a006.35
_223
100 1 _aAtanasova, Pepa.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
245 1 0 _aAccountable and Explainable Methods for Complex Reasoning over Text
_h[electronic resource] /
_cby Pepa Atanasova.
250 _a1st ed. 2024.
264 1 _aCham :
_bSpringer Nature Switzerland :
_bImprint: Springer,
_c2024.
300 _aXVIII, 199 p. 24 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
505 0 _a1. 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 _aThis 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 _aNatural language processing (Computer science).
650 0 _aInformation storage and retrieval systems.
650 0 _aMachine learning.
650 1 4 _aNatural Language Processing (NLP).
650 2 4 _aInformation Storage and Retrieval.
650 2 4 _aMachine Learning.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031515170
776 0 8 _iPrinted edition:
_z9783031515194
856 4 0 _uhttps://doi.org/10.1007/978-3-031-51518-7
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
942 _cSPRINGER
999 _c187606
_d187606