Metraipolis › archive › dc_8a79de16c841

Sentence-Level Topic Modeling with Lexical and Contextual Evidence — arXiv:2610.23388

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23388
License (as archived)
CC0-1.0
Archived
2026-10-19T08:43:50.017Z
SHA-256 of the archived text
820d75b87b780dbad8aa33f7348dc0eac82433f609b9055711394d2a0f98fa8c
Stable URL of this page
https://metraipolis.com/documento/dc_8a79de16c841

How to cite

Sentence-Level Topic Modeling with Lexical and Contextual Evidence — arXiv:2610.23388 — arXiv (en), https://arxiv.org/abs/2610.23388 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a79de16c841 (Metraipolis archive dc_8a79de16c841, sha256 820d75b87b780dbad8aa33f7348dc0eac82433f609b9055711394d2a0f98fa8c)
BibTeX
@misc{dc8a79de16c841,
  title = {Sentence-Level Topic Modeling with Lexical and Contextual Evidence — arXiv:2610.23388},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23388},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a79de16c841; sha256 820d75b87b780dbad8aa33f7348dc0eac82433f609b9055711394d2a0f98fa8c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23388. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Topic modeling faces a fundamental granularity dilemma: probabilistic topic models assign topics at the word level, whereas transformer-based methods operate at the document level. The latter overlooks that real-world documents typically cover multiple topics, whereas the former relies on individual words, which rarely provide sufficient context to identify them. We introduce SentenceETM, a neural topic model that assigns a topic to each sentence by jointly using lexical and contextual evidence. Each topic is described both by a distribution over the vocabulary, defined through word embeddings, and by a Gaussian over sentence embeddings concentrated on a topic-specific low-dimensional subspace. The topic of a sentence generates both its words and its embedding and is marginalized exactly, so that its posterior combines the two sources of evidence. Document proportions are inferred with amortized variational inference, while the Gaussian parameters are re-estimated in closed form. Experiments show that SentenceETM consistently improves sentence-level topic assignment over state-of-the-art approaches, and a case study of a presidential debate shows how sentence-level topics reveal how candidates handle the same subjects.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.23388 — 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 2026-10-19T08:39:24.868Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).