shared-task

TextGraphs-13 Shared Task on Multi-Hop Inference Explanation Regeneration

WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets

Evaluation scripts for the 2019 machine translation quality estimation shared task

📄 Evidence Retrieval and Claim Verification for the FEVER shared task using Transformer Networks

TextGraphs-14 Shared Task on Multi-Hop Inference Explanation Regeneration

Public repository for the MultiGEC dataset.

UMUTeam at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Linguistic Features and Word Embeddings

SciVQA: Scientific Visual Question Answering shared task

Data for the HIPE 2026 shared task (CLEF 2026 Evaluation Lab)

This repository contains the models used by the CLUZH team for the SIGMORPHON 2022 shared tasks.

Official code for "Ketaba-OCR at AR-MS NakbaNLP 2026" — QLoRA fine-tuning of a specialized HTR model with Linear+Boost ensemble for Arabic manuscript recognition. 1st place per-line (CER 0.082) and 3rd place official leaderboard at NakbaNLP 2026 (LREC 2026).

This repository contains code for our paper in the Surface Realization Workshop 2018 at ACL, Melbourne

Code and data for the PragTag-2023 Shared Task

Baseline models for HIPE-2022

The first-ever small scale manually annotated corpus for abuse report identification

Code of system submitted for Noisy Text Shared Task 2 (Identification of informative COVID-19 English Tweets)

Additional experimental model for NakbaNLP 2026 Shared Task (AR-MS) — LoRA/DoRA fine-tuning of Qari-OCR (Qwen2-VL-2B) for Arabic handwritten manuscript recognition on the Omar Al-Saleh Memoir Collection (1951-1965).

Minimal zero-shot prompting baseline for HIPE-2026 shared task on person-place relation qualification.

Work for participating to SemEval25 Task 5 - LLMs4Subjects - with Annif

Arabic sentence segmentation system for the AraSeg 2026 shared task (ArabicNLP @ EMNLP 2026): fine-tuned Arabic-encoder ensemble + semi-Markov DP decoding. Ranked #1 on all four closed-track dev leaderboards.