Pretrained Transformers for Text Ranking

BERT and Beyond
Erscheinungsjahr 2021
ISBN: 978-1-63639-230-1
Verlag: Morgan & Claypool Publishers

Buch, Englisch, 325 Seiten, Hardback, Format (B × H): 152 mm x 229 mm

Reihe: Synthesis Lectures on Human Language Technologies

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing (NLP) applications. This book provides an overview of text ranking with neural network architectures known as transformers, of which BERT (Bidirectional Encoder Representations from Transformers) is the best-known example. The combination of transformers and self-supervised pretraining has been responsible for a paradigm shift in NLP, information retrieval (IR), and beyond.This book provides a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers who wish to pursue work in this area. It covers a wide range of modern techniques, grouped into two high-level categories: transformer models that perform reranking in multi-stage architectures and dense retrieval techniques that perform ranking directly. Two themes pervade the book: techniques for handling long documents, beyond typical sentence-by-sentence processing in NLP, and techniques for addressing the tradeoff between effectiveness (i.e., result quality) and efficiency (e.g., query latency, model and index size). Although transformer architectures and pretraining techniques are recent innovations, many aspects of how they are applied to text ranking are relatively well understood and represent mature techniques. However, there remain many open research questions, and thus in addition to laying out the foundations of pretrained transformers for text ranking, this book also attempts to prognosticate where the field is heading.

Autoren/Hrsg.

Fachgebiete

• Technische Wissenschaften Technik Allgemein Technik: Allgemeines
• Mathematik | Informatik Mathematik Numerik und Wissenschaftliches Rechnen Angewandte Mathematik, Mathematische Modelle
• Technische Wissenschaften Maschinenbau | Werkstoffkunde Maschinenbau

Inhaltsverzeichnis

- Preface
- Acknowledgments
- Introduction
- Setting the Stage
- Multi-Stage Architectures for Reranking
- Refining Query and Document Representations
- Learned Dense Representations for Ranking
- Future Directions and Conclusions
- Bibliography
- Authors' Biographies