Metraipolis › archive › dc_bf36c97f9908
Detection of Self-Introductions in Legislative Testimony — arXiv:2608.07891
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07891
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:49:50.131Z
- SHA-256 of the archived text
2b6ae95eccde93ccaacfc979fbbbbbc48537a7f01c08e088aa9e694da41c9344- Stable URL of this page
https://metraipolis.com/documento/dc_bf36c97f9908
How to cite
Detection of Self-Introductions in Legislative Testimony — arXiv:2608.07891 — arXiv (en), https://arxiv.org/abs/2608.07891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf36c97f9908 (Metraipolis archive dc_bf36c97f9908, sha256 2b6ae95eccde93ccaacfc979fbbbbbc48537a7f01c08e088aa9e694da41c9344)
BibTeX
@misc{dcbf36c97f9908,
title = {Detection of Self-Introductions in Legislative Testimony — arXiv:2608.07891},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07891},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf36c97f9908; sha256 2b6ae95eccde93ccaacfc979fbbbbbc48537a7f01c08e088aa9e694da41c9344},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-introductions are common in legislative committee testimonies. Successfully detecting them and extracting the speaker's name is enormously helpful in the task of speaker identification in the context of government meetings. In this paper, we present a pipeline for detection of self-introductions in legislative committee testimony using machine learning. We construct a training dataset from 1.54 million utterances spanning five state legislative sessions, apply a name-matching heuristic to generate automatic labels, and train three classifiers: a decision tree, random forest, and XGBoost to find self-introductions and extract the speaker's name. We construct a feature set combining bag-of-words, positional context, structural signals, introductory phrase indicators, and discourse context features. Among the three classifiers, XGBoost achieves the best performance with an F1 score of 0.9747 and the fewest total errors; adding fine-tuned BERT probability features improves this further. As an extension, we score the full candidate dataset with a fine-tuned BERT classifier and add BERT probability outputs as features. This BERT-augmented XGBoost model improves F1 from 0.9747 to 0.9782 and reduces total test errors from 241 to 207. The primary gain over the decision tree baseline (F1 0.9323) is driven by discourse context features and the boosting ensemble strategy; BERT provides a modest complementary signal. Analysis of false positives reveals that a minority are genuine self-introductions mislabeled due to name inconsistencies in the source data, indicating that measured metrics modestly understate true performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.07891 — 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 2026-10-19T08:49:41.838Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).