Metraipolis › archive › dc_ea0e360dbca6

Mixture of Decoders for Diverse Dialog Response Generation — arXiv:2610.00621

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00621
License (as archived): CC0-1.0
Archived: 2026-10-06T13:54:07.144Z
SHA-256 of the archived text: c70781084566404f655f315f7b33b1073b999b72349d4bee20b43b0579215310
Stable URL of this page: https://metraipolis.com/documento/dc_ea0e360dbca6

How to cite

Mixture of Decoders for Diverse Dialog Response Generation — arXiv:2610.00621 — arXiv (en), https://arxiv.org/abs/2610.00621 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea0e360dbca6 (Metraipolis archive dc_ea0e360dbca6, sha256 c70781084566404f655f315f7b33b1073b999b72349d4bee20b43b0579215310)

BibTeX

@misc{dcea0e360dbca6,
  title = {Mixture of Decoders for Diverse Dialog Response Generation — arXiv:2610.00621},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00621},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea0e360dbca6; sha256 c70781084566404f655f315f7b33b1073b999b72349d4bee20b43b0579215310},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00621. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mixture modeling is a long established machine learning technique for learning large sets of multi-modal data. While it is known that sequence-to-sequence models for dialog response generation suffer from the problem of low diversity, we hypothesize that it is because sequence-to-sequence models tend to learn a degenerate uni-modal distribution of responses. We then propose to incorporate a mixture of decoders into sequence-to-sequence models and try to make each decoder learn specialized topics in order to improve the diversity of generated responses. Our model is developed under the framework of conditional variational autoencoder (CVAE). We evaluate our approach on an open domain chat corpus and show improvement over strong baselines in quantitative measures and human evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.00621 — 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 2026-10-06T12:15:34.628Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).