Metraipolis › archive › dc_29db2c17fa54
Sparse PPMI Graph Averaging for Random Indexing Embeddings — arXiv:2608.05724
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05724
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:27:13.631Z
- SHA-256 of the archived text
603e57d96bfa3993779fce29a5170785a3643d4a1a35266c678009f55d6ba3b2- Stable URL of this page
https://metraipolis.com/documento/dc_29db2c17fa54
How to cite
Sparse PPMI Graph Averaging for Random Indexing Embeddings — arXiv:2608.05724 — arXiv (en), https://arxiv.org/abs/2608.05724 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29db2c17fa54 (Metraipolis archive dc_29db2c17fa54, sha256 603e57d96bfa3993779fce29a5170785a3643d4a1a35266c678009f55d6ba3b2)
BibTeX
@misc{dc29db2c17fa54,
title = {Sparse PPMI Graph Averaging for Random Indexing Embeddings — arXiv:2608.05724},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05724},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29db2c17fa54; sha256 603e57d96bfa3993779fce29a5170785a3643d4a1a35266c678009f55d6ba3b2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05724. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study a specific sparse post-processing pipeline for Random Indexing (RI) on kinship analogies in a small fairytales corpus. The published artifacts use uniform RI context accumulation with 200 dimensions and eight nonzeros, followed by one residual graph average, $\mathbf{E}=(1-\alpha)\mathbf{E}_0+\alpha\mathbf{P}\mathbf{E}_0$, where $\mathbf{P}$ is a row-normalized PPMI graph and $\alpha=0.3$. Terminal row normalization and per-dimension median/IQR scaling are then applied. On the Google analogy benchmark's family section, 272 of 506 questions are valid for every seed. Across five paired seeds, the complete pipeline raises accuracy from 19.41\% to 30.74\%, a gain of 11.32 percentage points with a nested-bootstrap 95\% confidence interval of [6.93, 15.89]. Robust scaling alone contributes 3.24 points [1.25, 5.38], while graph averaging without robust scaling contributes 6.18 points [2.63, 9.92]. A separate 40-question general grid does not support a general improvement: the full pipeline changes accuracy by -6.00 points [-13.50, -0.50], and averaging without robust scaling changes it by -6.50 points [-14.50, -0.50]. The supported positive claim is therefore limited to the covered fairytales kinship analogy set; the results do not establish a generally effective embedding method.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.05724 — 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 2026-10-25T21:24:38.200Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).