# Searching for Sound-Meaning Collisions: Graph-Based Affordance Retrieval and Multi-Evaluator Ranking for Pun Translation at CLEF 2026 JOKER Task 2

arXiv: https://arxiv.org/abs/2608.04299 · HTML: https://mlsanity.com/paper/2608.04299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation](https://mlsanity.com/paper/2312.02439/) (2023)
- [Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps](https://mlsanity.com/paper/2410.10370/) (2024)
- [Crowd Score: A Method for the Evaluation of Jokes using Large Language Model AI Voters as Judges](https://mlsanity.com/paper/2212.11214/) (2022)
- [MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language](https://mlsanity.com/paper/2406.13698/) (2024)
- [Phonetic Word Embeddings](https://mlsanity.com/paper/2109.14796/) (2021)
- [Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings for CLEF JOKER 2025 Task 2](https://mlsanity.com/paper/2507.06506/) (2025)

## Abstract (arXiv)

Fifteen years ago, Low proposed that pun translators should stop searching for equivalent words and instead search for new points of contact between sound and meaning. In this paper, we investigate that idea computationally. We model pun translation as a process of discovery, exploration, and selection. A retrieval system searches semantic and phonological neighborhoods for target-language affordances: sound-meaning bridges that may support new wordplay. Multiple language models then explore these opportunities by generating competing translations, while a multi-perspective generate-and-rank architecture selects among them. Beyond system development, our primary contribution is an analysis of how retrieved affordances propagate through the translation process. We find that generators actively exploit retrieved opportunities, evaluators progressively concentrate around stronger sound-meaning bridges, and exact phonological collisions are selected at disproportionately high rates when available. At the same time, many puns still yield no usable affordances, suggesting that retrieval remains the central bottleneck in computational pun translation. The resulting picture is remarkably close to the process envisioned by Low. Successful pun translation emerges not from preserving source-language words, but from discovering new places in the target language where sound and meaning collide.