Metraipolis › archive › dc_cb56ecc49fcc

Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings — arXiv:2608.04311

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04311
License (as archived): CC0-1.0
Archived: 2026-10-31T11:24:36.101Z
SHA-256 of the archived text: ba82c7dd19a6c0b7cb8df1d2b322f7c4c17082f8b55b65c808b5d5745a6f6a9a
Stable URL of this page: https://metraipolis.com/documento/dc_cb56ecc49fcc

How to cite

Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings — arXiv:2608.04311 — arXiv (en), https://arxiv.org/abs/2608.04311 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb56ecc49fcc (Metraipolis archive dc_cb56ecc49fcc, sha256 ba82c7dd19a6c0b7cb8df1d2b322f7c4c17082f8b55b65c808b5d5745a6f6a9a)

BibTeX

@misc{dccb56ecc49fcc,
  title = {Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings — arXiv:2608.04311},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04311},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb56ecc49fcc; sha256 ba82c7dd19a6c0b7cb8df1d2b322f7c4c17082f8b55b65c808b5d5745a6f6a9a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04311. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Translating wordplay across languages has long challenged both professional translators and machine translation systems. We investigate three approaches to translating puns from English to French by combining large language models with linguistic constraints for wordplay generation. Our baseline uses a large language model with feedback from a discriminator prompted with positive and negative French examples. Our guided reasoning pipeline uses combined phonetic-semantic embeddings to retrieve lexical candidates for wordplay generation. Finally, our multi-agent framework iteratively evaluates and regenerates candidate translations using specialized feedback. Moving beyond literal translation, our objective is to preserve the linguistic creativity, ambiguity, and humor of the source-text wordplay rather than simply reproduce its vocabulary. The multi-agent and guided chain-of-thought systems ranked first and second, respectively, in the CLEF JOKER 2025 Task 2 competition under expert human evaluation, despite only modest improvements in BLEU and BERTScore. These findings suggest that both explicit phonetic-semantic guidance and iterative multi-agent evaluation can improve LLM-based wordplay translation relative to direct discriminator-guided generation, particularly when balancing semantic fidelity, phonetic similarity, and natural target-language expression

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.04311 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T11:13:23.161Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).