|
--- |
|
language: |
|
- tr |
|
tags: |
|
- subjectivity |
|
- CLEF2023 |
|
--- |
|
|
|
Fine-tuned [mDeBERTa V3](https://huggingface.co/microsoft/mdeberta-v3-base) model for subjectivity detection in newspaper sentences. |
|
This model was developed as part of the CLEF 2023 CheckThat! Lab [Task 2: Subjectivity in News Articles](https://checkthat.gitlab.io/clef2023/task2/). |
|
|
|
The goal in this task is to detect whether a sentence is objective (OBJ) or subjective (SUBJ). A sentence is subjective if its content is based on or influenced by personal feelings, tastes, or |
|
opinions. Otherwise, the sentence is objective. [(Antici et al., 2023)](https://ceur-ws.org/Vol-3370/paper10.pdf). |
|
|
|
The model was fine-tuned using a multilingual training and Turkish development dataset, for which the following (hyper)parameters were utilized: |
|
``` |
|
Batch Size = 64 |
|
Max Epochs = 2 |
|
Learning Rate = 6e-5 |
|
Warmup Steps = 300 |
|
Weight Decay = 0.1 |
|
``` |
|
|
|
The model ranked first in the CheckThat! Lab and obtained a macro F1 of 0.90 and a SUBJ F1 of 0.91. |
|
|
|
*DISCLAIMER*: the Turkish data was obtained from Tweets rather than newspaper articles. |
