Metraipolis › archive › dc_500680164ee5

Linguistic Features for Interpretable Textual Entailment — arXiv:2609.24932

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24932
License (as archived)
CC0-1.0
Archived
2026-10-09T06:50:17.631Z
SHA-256 of the archived text
0bf8680ed45556009e1f0071ebf6b74cd096e9e765eeb5123aad8bde09aaf495
Stable URL of this page
https://metraipolis.com/documento/dc_500680164ee5

How to cite

Linguistic Features for Interpretable Textual Entailment — arXiv:2609.24932 — arXiv (en), https://arxiv.org/abs/2609.24932 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_500680164ee5 (Metraipolis archive dc_500680164ee5, sha256 0bf8680ed45556009e1f0071ebf6b74cd096e9e765eeb5123aad8bde09aaf495)
BibTeX
@misc{dc500680164ee5,
  title = {Linguistic Features for Interpretable Textual Entailment — arXiv:2609.24932},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24932},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_500680164ee5; sha256 0bf8680ed45556009e1f0071ebf6b74cd096e9e765eeb5123aad8bde09aaf495},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24932. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the success of neural models in natural language processing, their black-box nature limits interpretability and conceals the linguistic phenomena underlying their predictions. We present SLITE, an explainable hybrid model for Recognizing Textual Entailment that integrates two complementary layers of semantic analysis: a structural-relational layer, based on semantic compatibility and incompatibility between compositional entities, and a distributional-informational layer, based on structured patterns of information change between embedding-based representations of the premise and the hypothesis. We propose 17 features that combine entity-level semantic relations, polarity-sensitive lexical matching, and alignment measures over semantic sub-representations of the similarity matrix, including measures based on entropy and transfer entropy. A logistic regression trained on these features achieves an accuracy of 83% on three-class SICK and 96% on SICK-CE, outperforming IsoLex by 4 percentage points and falling within 2 percentage points of RoBERTa with a fraction of its computational complexity. Ablation studies and SHAP analysis confirm that structural-relational features are the primary drivers of classification, while distributional-informational features provide essential complementary contributions, particularly for detecting neutrality and contradiction. Our results demonstrate that further exploration of hybrid approaches is a viable and scientifically productive alternative to massive neural architectures, and we hope they will strengthen the dialogue between linguistic theory and computational modeling of inference

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Symbolic Computation (cs.SC).
Pagina del lavoro: https://arxiv.org/abs/2609.24932 — 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 2026-10-09T06:48:45.073Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).