Metraipolis › archive › dc_2eede9cfdfb4

Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach — arXiv:2609.33121

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33121
License (as archived): CC0-1.0
Archived: 2026-10-07T21:52:38.382Z
SHA-256 of the archived text: f9d162c3ce792544cd2b2e4cb35f8c6653955c04e4d16e125fc32c61c101894b
Stable URL of this page: https://metraipolis.com/documento/dc_2eede9cfdfb4

How to cite

Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach — arXiv:2609.33121 — arXiv (en), https://arxiv.org/abs/2609.33121 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2eede9cfdfb4 (Metraipolis archive dc_2eede9cfdfb4, sha256 f9d162c3ce792544cd2b2e4cb35f8c6653955c04e4d16e125fc32c61c101894b)

BibTeX

@misc{dc2eede9cfdfb4,
  title = {Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach — arXiv:2609.33121},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33121},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2eede9cfdfb4; sha256 f9d162c3ce792544cd2b2e4cb35f8c6653955c04e4d16e125fc32c61c101894b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33121. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Computational methods have consistently struggled to determine the dominant temporal orientation of a sentence. This difficulty is especially pronounced when a sentence contains multiple embedded clauses with competing tense and aspectual information. To address this difficulty, we propose an alternative approach for identifying a sentence's past, present, or future global reference interval. Our method does not use any form of pretrained embeddings. We rather encode sentences using fixed-length inventory vectors that are comprised of part-of-speech counts, dependency relation counts, and explicit futurate pattern counts. We term this inventory vector of a sentence a "Morphosyntacton". The method does not use any padding, sequence models, or large language models. Evaluation on 1,799 syntactically complex English sentences, annotated as past, present or future, shows balanced and high accuracy multiclass classification, achieving an overall multi-class accuracy of 92%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.33121 — 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 2026-10-07T21:27:08.483Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).