dc.contributor.author | Layegh, Amirhossein | |
dc.contributor.author | Hossein Payberah, Amir | |
dc.contributor.author | Soylu, Ahmet | |
dc.contributor.author | Roman, Dumitru | |
dc.contributor.author | Matskin, Mihhail | |
dc.date.accessioned | 2024-01-29T15:13:33Z | |
dc.date.available | 2024-01-29T15:13:33Z | |
dc.date.created | 2023-08-31T13:10:16Z | |
dc.date.issued | 2023 | |
dc.identifier.isbn | 979-8-3503-2697-0 | |
dc.identifier.isbn | 979-8-3503-2698-7 | |
dc.identifier.uri | https://hdl.handle.net/11250/3114381 | |
dc.description.abstract | Prompt-based language models have produced encouraging results in numerous applications, including Named Entity Recognition (NER) tasks. NER aims to identify entities in a sentence and provide their types. However, the strong performance of most available NER approaches is heavily dependent on the design of discrete prompts and a verbalizer to map the model-predicted outputs to entity categories, which are complicated undertakings. To address these challenges, we present ContrastNER, a prompt-based NER framework that employs both discrete and continuous tokens in prompts and uses a contrastive learning approach to learn the continuous prompts and forecast entity types. The experimental results demonstrate that ContrastNER obtains competitive performance to the state-of-the-art NER methods in high-resource settings and outperforms the state-of-the-art models in low-resource circumstances without requiring extensive manual prompt engineering and verbalizer design. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.relation.ispartof | 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC) | |
dc.relation.ispartofseries | IEEE Annual International Computer Software and Applications Conference (COMPSAC); | |
dc.title | ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER | en_US |
dc.type | Chapter | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Conference object | en_US |
dc.description.version | acceptedVersion | en_US |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |
dc.identifier.doi | https://doi.org/10.1109/COMPSAC57700.2023.00038 | |
dc.identifier.cristin | 2171388 | |
dc.relation.project | Norges forskningsråd: 309691 | en_US |
dc.relation.project | EU – Horisont Europa (EC/HEU): 101093202 | en_US |
dc.relation.project | EU – Horisont Europa (EC/HEU): 101093216 | en_US |
dc.relation.project | Vetenskapsrådet: 2018-05973 | en_US |
dc.relation.project | EC/H2020/101016835 | en_US |
dc.relation.project | EU – Horisont Europa (EC/HEU): 101070284 | en_US |