Knowledge Sources

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AFFSZ4CN2" target="_blank" >RIV/00216208:11320/25:FFSZ4CN2 - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204302789&doi=10.1007%2f978-981-97-0747-8_2&partnerID=40&md5=a0e5f0e5fb735802f7235de962b44028" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204302789&doi=10.1007%2f978-981-97-0747-8_2&partnerID=40&md5=a0e5f0e5fb735802f7235de962b44028</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-981-97-0747-8_2" target="_blank" >10.1007/978-981-97-0747-8_2</a>

Result language

angličtina

Original language name

Knowledge Sources

Original language description

Knowledge sources are essential components of many NLP tasks, such as question answering (Chen et al., Reading wikipedia to answer open-domain questions. Preprint, 2017), fact verification (Thorne et al., Fever: a large-scale dataset for fact extraction and verification. Preprint, 2018), entity linking (Guo and Barbosa, Semantic Web 9(4):459–479, 2018; Josifoski et al., Zero-shot entity linking with dense entity retrieval. EMNLP, 2020), slot filling (Levy et al., Zero-shot relation extraction via reading comprehension. Preprint, 2017), dialogue (Dinan et al., Wizard of wikipedia: Knowledge-powered conversational agents. Preprint, 2018), etc. One task can also be the knowledge source for another task, such part-of-speech tagging (Schmid, Part-of-speech tagging with neural networks. Preprint, 1994) for dependency parsing (Qi et al., Universal dependency parsing from scratch. Preprint, 2019), etc. However, the availability, quality, and suitability of different types of knowledge sources vary depending on the domain, language, and task requirements. This chapter provides a comprehensive overview of the main types of knowledge sources used in NLP, such as statistical models, knowledge bases, task specific corpus with human annotations, etc. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Czech name

—

Czech description

—

Type

C - Chapter in a specialist book

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name

Knowledge-augmented Methods for Natural Language Processing

ISBN

978-981-9707-49-2

Number of pages of the result

15

Pages from-to

7-21

Number of pages of the book

255

Publisher name

Springer

Place of publication

—

UT code for WoS chapter

—