Metraipolis › archive › dc_605bb56c35d4

Compound interpretation is based on analogy — arXiv:2610.01688

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01688
License (as archived)
CC0-1.0
Archived
2026-10-06T13:55:54.313Z
SHA-256 of the archived text
c40be9c89c1389b1f3fd9f454740bdccdae8e8f9e39ac63daa9741984f42647f
Stable URL of this page
https://metraipolis.com/documento/dc_605bb56c35d4

How to cite

Compound interpretation is based on analogy — arXiv:2610.01688 — arXiv (en), https://arxiv.org/abs/2610.01688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_605bb56c35d4 (Metraipolis archive dc_605bb56c35d4, sha256 c40be9c89c1389b1f3fd9f454740bdccdae8e8f9e39ac63daa9741984f42647f)
BibTeX
@misc{dc605bb56c35d4,
  title = {Compound interpretation is based on analogy — arXiv:2610.01688},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01688},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_605bb56c35d4; sha256 c40be9c89c1389b1f3fd9f454740bdccdae8e8f9e39ac63daa9741984f42647f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How compound meanings are best predicted from constituent meanings remains a central question in computational models of lexical semantics. Comparing different computational models provides a way to evaluate alternative accounts of how semantic information is combined during compound comprehension. We propose a new model, the Compound Analogy Model (CAM), that predicts a compound's embedding by adding its constituent embeddings together with the average shift vectors of the two constituents' compound families. The resulting model is parameter-free and exploits local analogical structure in the semantic space. We evaluated CAM against the CAOSS model on Mandarin Chinese compounds. CAM consistently achieved higher prediction accuracy than CAOSS on both training and held-out data, with the exception of three-character compounds, for which analogical generalization is constrained by both small constituent families and a pronounced imbalance in family size between the two constituents. The advantage of CAM remained when evaluation was based on frequency-defined train-test splits that better approximate generalization from familiar to novel compounds. To assess the cognitive plausibility of the two models, we further examined whether model-derived semantic measures predict visual lexical decision latencies for two-character compounds. Predictors derived from CAM provided improved prediction for response latencies compared to predictors derived from the CAOSS model. These findings indicate that compound meaning is better characterized as local analogical generalization than as the application of a learned global linear transformation, and demonstrate that analogical semantic structure provides a cognitively plausible basis for compound comprehension.

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/2610.01688 — 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 2026-10-06T12:15:34.738Z 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).