000 04226nam a22005535i 4500
001 978-3-031-02181-7
003 DE-He213
005 20240730163831.0
007 cr nn 008mamaa
008 220601s2022 sz | s |||| 0|eng d
020 _a9783031021817
_9978-3-031-02181-7
024 7 _a10.1007/978-3-031-02181-7
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
100 1 _aLin, Jimmy.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_980724
245 1 0 _aPretrained Transformers for Text Ranking
_h[electronic resource] :
_bBERT and Beyond /
_cby Jimmy Lin, Rodrigo Nogueira, Andrew Yates.
250 _a1st ed. 2022.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2022.
300 _aXVII, 307 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSynthesis Lectures on Human Language Technologies,
_x1947-4059
505 0 _aPreface -- 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.
520 _aThe 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 inmulti-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.
650 0 _aArtificial intelligence.
_93407
650 0 _aNatural language processing (Computer science).
_94741
650 0 _aComputational linguistics.
_96146
650 1 4 _aArtificial Intelligence.
_93407
650 2 4 _aNatural Language Processing (NLP).
_931587
650 2 4 _aComputational Linguistics.
_96146
700 1 _aNogueira, Rodrigo.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_980725
700 1 _aYates, Andrew.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_980726
710 2 _aSpringerLink (Online service)
_980727
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031001925
776 0 8 _iPrinted edition:
_z9783031010538
776 0 8 _iPrinted edition:
_z9783031033094
830 0 _aSynthesis Lectures on Human Language Technologies,
_x1947-4059
_980728
856 4 0 _uhttps://doi.org/10.1007/978-3-031-02181-7
912 _aZDB-2-SXSC
942 _cEBK
999 _c85023
_d85023