Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915360018530304 |
|---|---|
| author | Chun, Yongchan Kim, Minhyuk Kim, Dongjun Park, Chanjun Lim, Heuiseok |
| author_facet | Chun, Yongchan Kim, Minhyuk Kim, Dongjun Park, Chanjun Lim, Heuiseok |
| contents | Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various NLP tasks, their potential for ATE has scarcely been examined. We propose a retrieval-based prompting strategy that, in the few-shot setting, selects demonstrations according to \emph{syntactic} rather than semantic similarity. This syntactic retrieval method is domain-agnostic and provides more reliable guidance for capturing term boundaries. We evaluate the approach in both in-domain and cross-domain settings, analyzing how lexical overlap between the query sentence and its retrieved examples affects performance. Experiments on three specialized ATE benchmarks show that syntactic retrieval improves F1-score. These findings highlight the importance of syntactic cues when adapting LLMs to terminology-extraction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21222 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval Chun, Yongchan Kim, Minhyuk Kim, Dongjun Park, Chanjun Lim, Heuiseok Computation and Language Information Retrieval Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various NLP tasks, their potential for ATE has scarcely been examined. We propose a retrieval-based prompting strategy that, in the few-shot setting, selects demonstrations according to \emph{syntactic} rather than semantic similarity. This syntactic retrieval method is domain-agnostic and provides more reliable guidance for capturing term boundaries. We evaluate the approach in both in-domain and cross-domain settings, analyzing how lexical overlap between the query sentence and its retrieved examples affects performance. Experiments on three specialized ATE benchmarks show that syntactic retrieval improves F1-score. These findings highlight the importance of syntactic cues when adapting LLMs to terminology-extraction tasks. |
| title | Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2506.21222 |