Papers › TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers

TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers

19 Apr 2021archive 2025-07-28

Khyati Mahajan, Erfan Al-Hossami, Samira Shaikh

In this paper, we describe our approach towards utilizing pre-trained models for the task of hope speech detection. We participated in Task 2: Hope Speech Detection for Equality, Diversity and Inclusion at LT-EDI-2021 @ EACL2021. The goal of this task is to predict the presence of hope speech, along with the presence of samples that do not belong to the same language in the dataset. We describe our approach to fine-tuning RoBERTa for Hope Speech detection in English and our approach to fine-tuning XLM-RoBERTa for Hope Speech detection in Tamil and Malayalam, two low resource Indic languages. We demonstrate the performance of our approach on classifying text into hope-speech, non-hope and not-language. Our approach ranked 1st in English (F1 = 0.93), 1st in Tamil (F1 = 0.61) and 3rd in Malayalam (F1 = 0.83).

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityHope Speech DetectionHope Speech Detection for EnglishHope Speech Detection for MalayalamHope Speech Detection for TamilTask 2Text ClassificationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hope Speech Detection HopeEDI RoBERTa Weighted Average F1-score 0.93 #1 of 2 Archive leaderboard report
Hope Speech Detection for English HopeEDI RoBERTa Weighted Average F1-score 0.93 #1 of 2 Archive leaderboard report
Hope Speech Detection for Malayalam HopeEDI XLM-RoBERTa Weighted Average F1-score 0.87 #1 of 2 Archive leaderboard report
Hope Speech Detection for Tamil HopeEDI XLM-RoBERTa Weighted Average F1-score 0.60 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionRoBERTaSoftmaxWeight DecayWordPieceXLM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections