Overview of the HASOC Subtrack at FIRE 2023: Hate-Speech Identification in Sinhala and Gujarati
Bibliographic record
Abstract
Detecting offensive and hateful content in low-resource languages poses a significant challenge due to the limited availability of benchmark datasets. It is crucial to address this gap by creating benchmark datasets tailored to these languages. This not only enhances the accuracy of detection but also provides valuable insights into the efficacy of identifying problematic content in comparison to high-resource languages. In line with this commitment to advancing research on low-resource languages, the Hate Speech and Offensive Content Identification (HASOC) shared task introduced a dedicated subtrack for Hate Speech Identification in Sinhala and Gujarati in 2023. This paper outlines the objectives of the task, discusses the characteristics of the data involved, and presents an analysis of the participants� submissions. For Task 1a, we utilized an existing Sinhala dataset (SOLD) consisting of 10,000 tweets. Meanwhile, for Task 1b, focused on Gujarati, we curated a new dataset comprising 1,020 tweets. A total of 16 teams submitted experiments for Sinhala, with the leading team achieving an impressive F1 score of 0.83. In the case of the Gujarati task, 17 teams participated, and the highest-performing team achieved an F1 score of 0.84. These results highlight the significance of tailored datasets in facilitating the effective detection of offensive content in low-resource languages. © 2023 Copyright for this paper by its authors.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.008 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".