TartuNLP at EvaLatin 2024: Emotion Polarity Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916513615708160 |
|---|---|
| author | Dorkin, Aleksei Sirts, Kairit |
| author_facet | Dorkin, Aleksei Sirts, Kairit |
| contents | This paper presents the TartuNLP team submission to EvaLatin 2024 shared task of the emotion polarity detection for historical Latin texts. Our system relies on two distinct approaches to annotating training data for supervised learning: 1) creating heuristics-based labels by adopting the polarity lexicon provided by the organizers and 2) generating labels with GPT4. We employed parameter efficient fine-tuning using the adapters framework and experimented with both monolingual and cross-lingual knowledge transfer for training language and task adapters. Our submission with the LLM-generated labels achieved the overall first place in the emotion polarity detection task. Our results show that LLM-based annotations show promising results on texts in Latin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_01159 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TartuNLP at EvaLatin 2024: Emotion Polarity Detection Dorkin, Aleksei Sirts, Kairit Computation and Language This paper presents the TartuNLP team submission to EvaLatin 2024 shared task of the emotion polarity detection for historical Latin texts. Our system relies on two distinct approaches to annotating training data for supervised learning: 1) creating heuristics-based labels by adopting the polarity lexicon provided by the organizers and 2) generating labels with GPT4. We employed parameter efficient fine-tuning using the adapters framework and experimented with both monolingual and cross-lingual knowledge transfer for training language and task adapters. Our submission with the LLM-generated labels achieved the overall first place in the emotion polarity detection task. Our results show that LLM-based annotations show promising results on texts in Latin. |
| title | TartuNLP at EvaLatin 2024: Emotion Polarity Detection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.01159 |