Metraipolis › archive › dc_2770cd64b683

Logical Embeddings for Argument Analysis — arXiv:2608.15325

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15325
License (as archived)
CC0-1.0
Archived
2026-10-18T18:03:05.412Z
SHA-256 of the archived text
56d34d6cbed2ac5396d4945e86c25cd8ab66f7351cb7a0638cf4b5f7e394f03f
Stable URL of this page
https://metraipolis.com/documento/dc_2770cd64b683

How to cite

Logical Embeddings for Argument Analysis — arXiv:2608.15325 — arXiv (en), https://arxiv.org/abs/2608.15325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2770cd64b683 (Metraipolis archive dc_2770cd64b683, sha256 56d34d6cbed2ac5396d4945e86c25cd8ab66f7351cb7a0638cf4b5f7e394f03f)
BibTeX
@misc{dc2770cd64b683,
  title = {Logical Embeddings for Argument Analysis — arXiv:2608.15325},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15325},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2770cd64b683; sha256 56d34d6cbed2ac5396d4945e86c25cd8ab66f7351cb7a0638cf4b5f7e394f03f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a new framework for machine-learning-oriented argument analysis tasks. Our proposal involves replacing traditional contextualized word embeddings used in most NLP tasks with logical embeddings, an alternative encoding that directly exploits argumentation structures. In essence, logical embeddings encapsulate the logical semantics of an argument, allowing for a better representation of its meaning. Supporting these embeddings is a mathematical logic-based similarity measure that offers a transparent notion of proximity and is guaranteed to satisfy several desirable theoretical properties that current cosine similarity-based contextualized word embeddings cannot assure. This similarity measure induces a positive semi-definite kernel on the set of arguments, enabling us to uniquely define logical embeddings using the theory of Reproducing Kernel Hilbert Spaces (RKHS). Moreover, we prove that this encoding is optimal, in the sense that no logical information is lost in the process. As with other RKHS applications, logical embeddings can be used in numerous supervised and unsupervised tasks. We provide an implementation of the method and aim to test it against literature benchmarks. Additionally, we demonstrate that logical embeddings outperform most standard embedding methods on a classification task.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15325 — 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 2026-10-18T16:29:14.007Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).