迷失在语音中：超越标准UD假设的口语双语会话的基准测试、评估与解析
Lost in Speech: Benchmarking, Evaluation, and Parsing of Spoken Bilingual Conversational Language Beyond Standard UD Assumptions
AI总结：
针对口语双语会话中的不流利和话语驱动结构，提出SpokeBench基准、Flex-UD评估指标和DECAP解析框架，显著提升依赖解析性能。
摘要：
口语双语会话给句法解析带来了重大挑战，因为它们通常包含不流利和话语驱动的结构，这些结构在标准的通用依赖（UD）假设和评估实践下使依赖解析复杂化。为了系统研究这些挑战，本文首先引入了一个基于语言学的会话双语现象分类法，以及SpokeBench，一个由专家标注的英语-西班牙语基准，用于结构复杂的语音。为了解决现有评估实践的局限性，我们提出了Flex-UD，一种歧义感知的评估指标，能够区分灾难性的结构失败和语言上可接受的变体。最后，我们引入了DECAP，一种解耦的代理解析框架，将口语现象处理与核心句法分析分离，无需重新训练即可实现鲁棒且可解释的依赖解析。在专有和开源大语言模型上的实验表明，DECAP在复杂的会话现象上显著提高了性能，在UPOS-F1分数上比基线提高了超过60%，而Flex-UD评估揭示了在标准基于附着的指标下部分隐藏的增益。
英文摘要：
Spoken bilingual conversations pose substantial challenges for syntactic parsing because they often include disfluencies and discourse-driven structures that complicate dependency parsing under standard Universal Dependencies (UD) assumptions and evaluation practices. To systematically study these challenges, in this work, we first introduce a linguistically grounded taxonomy of conversational bilingual phenomena, together with SpokeBench, an expert-annotated English-Spanish benchmark for structurally complex speech. To address the limitations of existing evaluation practices, we propose Flex-UD, an ambiguity-aware evaluation metric that distinguishes catastrophic structural failures from linguistically acceptable variations. Finally, we introduce DECAP, a decoupled agentic parsing framework that separates spoken-phenomena handling from core syntactic analysis, enabling robust and interpretable dependency parsing without retraining. Experiments across both proprietary and open-weight LLMs show that DECAP substantially improves performance on complex conversational phenomena and achieves over 60% improvements in UPOS-F1 Score over baselines, while Flex-UD evaluations reveal gains that otherwise remain partially hidden under standard attachment-based metrics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
