04595nam a22006015i 4500 978-981-97-0747-8 DE-He213 20251030111809.0 cr nn 008mamaa 240408s2024 si | s |||| 0|eng d 9789819707478 978-981-97-0747-8 10.1007/978-981-97-0747-8 doi QA76.9.N38 UYQL bicssc COM073000 bisacsh UYQL thema Jiang, Meng. author. (orcid)0000-0002-3009-519X https://orcid.org/0000-0002-3009-519X aut http://id.loc.gov/vocabulary/relators/aut 74859 Knowledge-augmented Methods for Natural Language Processing [electronic resource] / by Meng Jiang, Bill Yuchen Lin, Shuohang Wang, Yichong Xu, Wenhao Yu, Chenguang Zhu. 1st ed. 2024. Singapore : Springer Nature Singapore : Imprint: Springer, 2024. IX, 95 p. 18 illus., 15 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda SpringerBriefs in Computer Science, 2191-5776 Chapter 1. Introduction to Knowledge-augmented NLP -- Chapter 2. Knowledge Sources -- Chapter 3. Knowledge-augmented Methods for Natural Language Understanding -- Chapter 4. Knowledge-augmented Methods for Natural Language Generation -- Chapter 5. Augmenting NLP Models with Commonsense Knowledge -- Chapter 6. Summary and Future Directions. Over the last few years, natural language processing has seen remarkable progress due to the emergence of larger-scale models, better training techniques, and greater availability of data. Examples of these advancements include GPT-4, ChatGPT, and other pre-trained language models. These models are capable of characterizing linguistic patterns and generating context-aware representations, resulting in high-quality output. However, these models rely solely on input-output pairs during training and, therefore, struggle to incorporate external world knowledge, such as named entities, their relations, common sense, and domain-specific content. Incorporating knowledge into the training and inference of language models is critical to their ability to represent language accurately. Additionally, knowledge is essential in achieving higher levels of intelligence that cannot be attained through statistical learning of input text patterns alone. In this book, we will review recent developments in the field of natural language processing, specifically focusing on the role of knowledge in language representation. We will examine how pre-trained language models like GPT-4 and ChatGPT are limited in their ability to capture external world knowledge and explore various approaches to incorporate knowledge into language models. Additionally, we will discuss the significance of knowledge in enabling higher levels of intelligence that go beyond statistical learning on input text patterns. Overall, this survey aims to provide insights into the importance of knowledge in natural language processing and highlight recent advances in this field. Natural language processing (Computer science). 65131 Computational linguistics. Data mining. 6941 Natural Language Processing (NLP). 66164 Computational Linguistics. Data Mining and Knowledge Discovery. Lin, Bill Yuchen. author. aut http://id.loc.gov/vocabulary/relators/aut 74860 Wang, Shuohang. author. aut http://id.loc.gov/vocabulary/relators/aut 74861 Xu, Yichong. author. aut http://id.loc.gov/vocabulary/relators/aut 74862 Yu, Wenhao. author. aut http://id.loc.gov/vocabulary/relators/aut 74863 Zhu, Chenguang. author. aut http://id.loc.gov/vocabulary/relators/aut 74864 SpringerLink (Online service) Springer Nature eBook Printed edition: 9789819707461 Printed edition: 9789819707485 Printed edition: 9789819707492 SpringerBriefs in Computer Science, 2191-5776 66578 https://doi.org/10.1007/978-981-97-0747-8 ZDB-2-SCS ZDB-2-SXCS 59007 59007