Metraipolis › archive › dc_7fb067f443f6
Reading the Neighborhood: Text-Attentive Graph Reranking for Automated Subject Indexing — arXiv:2610.20048
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20048
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:44:33.415Z
- SHA-256 of the archived text
d7a3fba259f0660cec48797268050eeb96f39f18fd492621013e2019e928a1be- Stable URL of this page
https://metraipolis.com/documento/dc_7fb067f443f6
How to cite
Reading the Neighborhood: Text-Attentive Graph Reranking for Automated Subject Indexing — arXiv:2610.20048 — arXiv (en), https://arxiv.org/abs/2610.20048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fb067f443f6 (Metraipolis archive dc_7fb067f443f6, sha256 d7a3fba259f0660cec48797268050eeb96f39f18fd492621013e2019e928a1be)
BibTeX
@misc{dc7fb067f443f6,
title = {Reading the Neighborhood: Text-Attentive Graph Reranking for Automated Subject Indexing — arXiv:2610.20048},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20048},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fb067f443f6; sha256 d7a3fba259f0660cec48797268050eeb96f39f18fd492621013e2019e928a1be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Subject indexing assigns descriptors from a controlled vocabulary to bibliographic records, a task characterized by thousands of labels, few positive examples per label, and a long tail of rarely used descriptors. Existing extreme multi-label classifiers treat the vocabulary as a flat list, ignoring the semantic relations that thesauri encode. We present TAGHN, a heterogeneous graph reranker over a per-document subgraph of retrieved candidates augmented with the thesaurus neighborhood. The relevance of a candidate descriptor is estimated jointly from its similarity with the document and also the degree to which the candidate's thesaurus neighborhood matches the document content. A decomposed scoring head combines interpretable graph-derived features with retrieval signals. On STW, an economic thesaurus of 6,198 descriptors, TAGHN reaches 0.380 macro F1 against 0.346 for a fine-tuned cross-encoder and 0.278 for a fixed-vocabulary XMLC classifier. In terms of micro F1, it outperforms reranking models and stays competitive (-3.0) with the best fixed-vocabulary XMLC model. Qualitative analysis shows the graph resolving errors that per-label scoring cannot, selecting a narrower gold descriptor where an unstructured reranker settles for its broader parent. Tema degli esploratori: ricerca e scienza aperta (elenco arXiv cs.DL, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Digital Libraries (cs.DL). Pagina del lavoro: https://arxiv.org/abs/2610.20048 — 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 2026-10-15T21:33:14.370Z dalla pagina https://arxiv.org/list/cs.DL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).