國立高雄大學圖資館 |

登入

回首頁

Accountable and explainable methods for complex reasoning over text

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Accountable and explainable methods for complex reasoning over textby Pepa Atanasova.
作者:	Atanasova, Pepa.
出版者:	Cham :Springer Nature Switzerland :2024.
面頁冊數:	xviii, 199 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Machine learning.
電子資源:	https://doi.org/10.1007/978-3-031-51518-7
ISBN:	9783031515187$q(electronic bk.)

Accountable and explainable methods for complex reasoning over text
Atanasova, Pepa.

Accountable and explainable methods for complex reasoning over text[electronic resource] /by Pepa Atanasova. - Cham :Springer Nature Switzerland :2024. - xviii, 199 p. :ill., digital ;24 cm.

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.

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.

ISBN: 9783031515187$q(electronic bk.)

Standard No.: 10.1007/978-3-031-51518-7doiSubjects--Topical Terms:

188639
Machine learning.

LC Class. No.: Q325.5

Dewey Class. No.: 006.31

Accountable and explainable methods for complex reasoning over text
LDR:02842nmm a2200325 a 4500 001 664446
003 DE-He213
005 20240406124731.0
006 m d
007 cr nn 008maaau
008 241219s2024 sz s 0 eng d
020 $a 9783031515187$q(electronic bk.)
020 $a 9783031515170$q(paper)
024 7 $a 10.1007/978-3-031-51518-7 $2 doi
035 $a 978-3-031-51518-7
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5
072 7 $a UYQL $2 bicssc
072 7 $a COM073000 $2 bisacsh
072 7 $a UYQL $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .A862 2024
100 1 $a Atanasova, Pepa. $3 977165
245 1 0 $a Accountable and explainable methods for complex reasoning over text $h [electronic resource] / $c by Pepa Atanasova.
260 $a Cham : $b Springer Nature Switzerland : $b Imprint: Springer, $c 2024.
300 $a xviii, 199 p. : $b ill., digital ; $c 24 cm.
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.
650 0 $a Machine learning. $3 188639
650 1 4 $a Natural Language Processing (NLP) $3 826373
650 2 4 $a Information Storage and Retrieval. $3 274190
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-031-51518-7
950 $a Computer Science (SpringerNature-11645)