SemEval-2025 Task 1: AdMIRe -- Advancing Multimodal Idiomaticity Representation
By: Thomas Pickard , Aline Villavicencio , Maggie Mi and more
Potential Business Impact:
Helps computers understand tricky sayings in pictures.
Idiomatic expressions present a unique challenge in NLP, as their meanings are often not directly inferable from their constituent words. Despite recent advancements in Large Language Models (LLMs), idiomaticity remains a significant obstacle to robust semantic representation. We present datasets and tasks for SemEval-2025 Task 1: AdMiRe (Advancing Multimodal Idiomaticity Representation), which challenges the community to assess and improve models' ability to interpret idiomatic expressions in multimodal contexts and in multiple languages. Participants competed in two subtasks: ranking images based on their alignment with idiomatic or literal meanings, and predicting the next image in a sequence. The most effective methods achieved human-level performance by leveraging pretrained LLMs and vision-language models in mixture-of-experts settings, with multiple queries used to smooth over the weaknesses in these models' representations of idiomaticity.
Similar Papers
NLP Datasets for Idiom and Figurative Language Tasks
Computation and Language
Helps computers understand jokes and slang.
Evaluating Large Language Models on Multiword Expressions in Multilingual and Code-Switched Contexts
Computation and Language
Computers still struggle with tricky word meanings.
Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors
Computation and Language
Helps computers understand different cultures' word pictures.