Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2410.22827 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914997960966144 |
|---|---|
| author | Johansson, Richard |
| author_facet | Johansson, Richard |
| contents | We evaluate a battery of recent large language models on two benchmarks for word sense disambiguation in Swedish. At present, all current models are less accurate than the best supervised disambiguators in cases where a training set is available, but most models outperform graph-based unsupervised systems. Different prompting approaches are compared, with a focus on how to express the set of possible senses in a given context. The best accuracies are achieved when human-written definitions of the senses are included in the prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22827 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How Well Do Large Language Models Disambiguate Swedish Words? Johansson, Richard Computation and Language We evaluate a battery of recent large language models on two benchmarks for word sense disambiguation in Swedish. At present, all current models are less accurate than the best supervised disambiguators in cases where a training set is available, but most models outperform graph-based unsupervised systems. Different prompting approaches are compared, with a focus on how to express the set of possible senses in a given context. The best accuracies are achieved when human-written definitions of the senses are included in the prompts. |
| title | How Well Do Large Language Models Disambiguate Swedish Words? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.22827 |