Multi-Figurative Language Generation (COLING 2022)

Data and code for the paper "ID10M: Idiom Identification in 10 Languages" (NAACL 2022).

𝗡𝗮𝘁𝘂𝗿𝗮𝗹 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 | 𝗖𝗦𝟲𝟬𝟬𝟳𝟱 | 𝗣𝗢𝗦 𝗧𝗮𝗴𝗴𝗶𝗻𝗴, 𝗠𝗶𝗻𝗶 𝗖𝗼𝗣𝗶𝗹𝗼𝘁, 𝗕𝗘𝗥𝗧

A Survey on Automatic Generation of Figurative Language: From Rule-based Systems to Large Language Models (ACM Computing Surveys)

Dataset and resources for the SIGTURK 2024 paper: 'Turkish Delights: A Dataset on Turkish Euphemisms'

The dataset contains texts about drug-trafficking in Spanish. Note that the copyrighted material, for instance, the literature and essay categories are not provided within the dataset. If you need a list of the material used in the experiments, please contact the authors.

Corpus and output files of article Frontiers in DH

Code for the paper "Character aware models with similarity learning for metaphor detection".

This repository contains a corpus compiled for the study of conceptual metaphors in mental health discourse. The dataset includes both annotated and unannotated materials and is intended to support research on metaphor identification, classification, and analysis in mental health-related texts.

This Repository contains the baselines for evaluation in HUHU shared task at Iberlef 2023

A unified benchmark for evaluating Bengali cultural reasoning in large language models across idioms, proverbs, riddles, and social norms, with a shared error taxonomy and prompt-sensitivity analysis across zero-shot, few-shot, and culturally primed conditions.