Recent advances in automatic term extraction : a comprehensive survey

Tran, Hanh Thi Hong (avtor), Martinc, Matej (avtor), Caporusso, Jaya (avtor), Delaunay, Julien (avtor), Doucet, Antoine (avtor), Pollak, Senja (avtor)

Automatic terminology or term extraction (ATE) is a Natural Language Processing (NLP) task intended to automatically identify specialized terms present in domain-specific corpora. As units of knowledge in a speciic ield of expertise, extracted terms are not only beneicial for several terminographical tasks, but also support and improve several complex downstream tasks, e.g., information retrieval, machine translation, topic detection, and sentiment analysis. ATE systems and datasets annotated for the task at hand have been studied and developed for decades, but more recent approaches have increasingly involved novel neural systems. Despite a large amount of new research on ATE tasks, systematic survey studies covering novel neural approaches are lacking, especially when it comes to the usage of large-scale language models (LLMs). We present a comprehensive survey of neural approaches to ATE, focusing on transformer-based neural models and the recent generative approaches based on LLMs. The study also compares these systems and previous ML-based approaches, which employed feature engineering and non-neural supervised learning algorithms.

• Jezik: Angleški jezik
• Ključne besede: computing methodologies, natural language processing, neural networks, language resources, language models, transformers, automatic term extraction, ATE, low-resourced languages, monolingual, multilingual, deep learning, zero-shot, few-shot, transfer learning, prompt engineering, large-scale language models, LLMs
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FRI - Fakulteta za računalništvo in informatiko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2026
• Št. strani: 34 str.
• Številčenje: Vol. , no.
• PID: 20.500.12556/RUL-179419
• UDK: 004.89:81'322
• ISSN pri članku: 0360-0300
• DOI: 10.1145/3787584
• COBISS.SI-ID: 268167171
• Datum objave v RUL: 13.02.2026

Gradivo je del revije

• Naslov: ACM computing surveys
• Skrajšan naslov: ACM comput. surv.
• Založnik: Association for Computing Machinery
• ISSN: 0360-0300
• COBISS.SI-ID: 24841216

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: računalniške metodologije, obdelava naravnega jezika, nevronske mreže, jezikovni viri, jezikovni modeli, transformatorji, avtomatsko pridobivanje izrazov, ATE, jeziki z malo viri, enojezični, večjezični, globoko učenje, učenje z ničelnim številom poskusov, učenje z malo poskusi, prenosno učenje, hitro inženirstvo, jezikovni modeli velikega obsega