Question Answering for the Curated Web
Tasks and Methods in QA over Knowledge Bases and Text Collections
Seiten
2021
Morgan & Claypool Publishers (Verlag)
978-1-63639-240-0 (ISBN)
Morgan & Claypool Publishers (Verlag)
978-1-63639-240-0 (ISBN)
Provides an overview of the state-of-the-art in question answering. The book covers the twin paradigms of curated Web sources used in QA tasks - trusted text collections like Wikipedia, and objective information distilled into large-scale knowledge bases.
Question answering (QA) systems on the Web try to provide crisp answers to information needs posed in natural language, replacing the traditional ranked list of documents. QA, posing a multitude of research challenges, has emerged as one of the most actively investigated topics in information retrieval, natural language processing, and the artificial intelligence communities today. The flip side of such diverse and active interest is that publications are highly fragmented across several venues in the above communities, making it very difficult for new entrants to the field to get a good overview of the topic.
Through this book, we make an attempt towards mitigating the above problem by providing an overview of the state-of-the-art in question answering. We cover the twin paradigms of curated Web sources used in QA tasks — trusted text collections like Wikipedia, and objective information distilled into large-scale knowledge bases. We discuss distinct methodologies that have been applied to solve the QA problem in both these paradigms, using instantiations of recent systems for illustration. We begin with an overview of the problem setup and evaluation, cover notable sub-topics like open-domain, multi-hop, and conversational QA in depth, and conclude with key insights and emerging topics. We believe that this resource is a valuable contribution towards a unified view on QA, helping graduate students and researchers planning to work on this topic in the near future.
Question answering (QA) systems on the Web try to provide crisp answers to information needs posed in natural language, replacing the traditional ranked list of documents. QA, posing a multitude of research challenges, has emerged as one of the most actively investigated topics in information retrieval, natural language processing, and the artificial intelligence communities today. The flip side of such diverse and active interest is that publications are highly fragmented across several venues in the above communities, making it very difficult for new entrants to the field to get a good overview of the topic.
Through this book, we make an attempt towards mitigating the above problem by providing an overview of the state-of-the-art in question answering. We cover the twin paradigms of curated Web sources used in QA tasks — trusted text collections like Wikipedia, and objective information distilled into large-scale knowledge bases. We discuss distinct methodologies that have been applied to solve the QA problem in both these paradigms, using instantiations of recent systems for illustration. We begin with an overview of the problem setup and evaluation, cover notable sub-topics like open-domain, multi-hop, and conversational QA in depth, and conclude with key insights and emerging topics. We believe that this resource is a valuable contribution towards a unified view on QA, helping graduate students and researchers planning to work on this topic in the near future.
Preface
Acknowledgments
Introduction
Setup
Getting Started with Simple Questions
Complex Question Answering
Conversational Question Answering
Part I: Summary and Insights
Setup
Reading Comprehension
Open-Domain Question Answering
Multi-Hop Question Answering
Conversational Question Answering
Part II: Summary and Insights
Open Directions
References
Authors' Biographies
| Erscheinungsdatum | 08.11.2021 |
|---|---|
| Reihe/Serie | Synthesis Lectures on Information Concepts, Retrieval, and Services |
| Verlagsort | San Rafael |
| Sprache | englisch |
| Maße | 152 x 229 mm |
| Themenwelt | Mathematik / Informatik ► Informatik ► Datenbanken |
| Informatik ► Software Entwicklung ► User Interfaces (HCI) | |
| Mathematik / Informatik ► Informatik ► Theorie / Studium | |
| ISBN-10 | 1-63639-240-7 / 1636392407 |
| ISBN-13 | 978-1-63639-240-0 / 9781636392400 |
| Zustand | Neuware |
| Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
Aus- und Weiterbildung nach iSAQB-Standard zum Certified Professional …
Buch | Hardcover (2023)
dpunkt Verlag
CHF 48,85
Lean UX und Design Thinking: Teambasierte Entwicklung …
Buch | Hardcover (2022)
dpunkt (Verlag)
CHF 48,85
Wissensverarbeitung - Neuronale Netze
Buch | Hardcover (2023)
Carl Hanser (Verlag)
CHF 48,95
