Discourse Analysis of Legislative Bill Discussions

Computer Science > Computation and Language arXiv:2611.05381 (cs) [Submitted on 30 Jul 2026] Title: Discourse Analysis of Legislative Bill Discussions Authors: Isaac Rudnick, Nipun Das, Foaad Khosmood.

计算机科学 > 计算与语言 arXiv:2611.05381 (cs) [提交于 2026 年 7 月 30 日] 标题：立法法案讨论的话语分析 作者：Isaac Rudnick, Nipun Das, Foaad Khosmood。

Abstract: Legislative hearings are distinct communication events with their own human recognizable structure and logic, yet they have been analyzed as distinct phenomena beyond their transcripts. Understanding legislative hearings at a deeper level is a major step in analyzing the work and power relationships within democratic bodies.

摘要：立法听证会是独特的交流事件，具有人类可识别的结构和逻辑，但以往对它们的研究往往局限于文字记录之外的独立现象。更深层次地理解立法听证会，是分析民主机构内部工作和权力关系的重要一步。

In this work, we present a novel end-to-end pipeline for parsing rhetorical structures from legislative committee hearings with the goal of improving legislative discourse analysis and democratic accountability. We also propose a rhetorical structure grammar and find that 55.21% of California state bill discussions in our dataset can be parsed with this grammar.

在这项工作中，我们提出了一种新颖的端到端流水线，用于解析立法委员会听证会中的修辞结构，旨在改善立法话语分析和民主问责制。我们还提出了一种修辞结构语法，并发现数据集中 55.21% 的加利福尼亚州法案讨论可以使用该语法进行解析。

We evaluate our pipeline with two utterance section classifiers on a random subset of over 2,000 annotated utterances corresponding to 100 hearings. We find that a logistic regression-based classifier with grammar-based output masking and utterance tag smoothing outperforms more complex models, achieving an F1 score of 52.8% against our ground truth discourse section labels.

我们使用两个话语部分分类器，在对应于 100 场听证会的 2,000 多条标注话语的随机子集上评估了我们的流水线。我们发现，一种结合了基于语法的输出掩码和话语标签平滑的逻辑回归分类器，其表现优于更复杂的模型，在我们的真实话语部分标签上达到了 52.8% 的 F1 分数。