预训练语言模型能否检测并理解语义欠明确性？问问 DUST！
Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
AI总结：
本文构建按类型分组的语义欠明确句子数据集 DUST，评估预训练语言模型的识别与解释能力，发现模型可识别欠明确句却难以正确解释且缺乏不确定性。
摘要：
在日常语言使用中，说话者经常说出并理解语义欠明确的句子，即其内容不足以完整传达信息或无法被单一明确地解释。例如，要理解欠明确的句子“Don't spend too much”（别花太多），该句隐含了（不）该花费什么这一信息，就需要额外的语言语境或外部知识。在本研究中，我们提出了一个新颖的按类型分组的语义欠明确句子数据集 DUST（Dataset of semantically Underspecified Sentences grouped by Type），并用其研究预训练语言模型（LM）能否正确识别和解释欠明确句子。我们发现，较新的 LM 在获得显式提示时，能够在一定程度上识别欠明确句子。然而，对任何 LM 而言，正确解释这些句子都要困难得多。实验表明，LM 在解释欠明确句子时几乎不表现出不确定性，这与欠明确性的理论解释所预测的情况相反。总体而言，本研究揭示了当前模型在句子语义处理方面的局限，并强调了在评估 LM 的语言能力时使用自然数据和交际场景的重要性。
英文摘要：
In everyday language use, speakers frequently utter and interpret sentences that are semantically underspecified, namely, whose content is insufficient to fully convey their message or interpret them univocally. For example, to interpret the underspecified sentence "Don't spend too much", which leaves implicit what (not) to spend, additional linguistic context or outside knowledge is needed. In this work, we propose a novel Dataset of semantically Underspecified Sentences grouped by Type (DUST) and use it to study whether pre-trained language models (LMs) correctly identify and interpret underspecified sentences. We find that newer LMs are reasonably able to identify underspecified sentences when explicitly prompted. However, interpreting them correctly is much harder for any LMs. Our experiments show that when interpreting underspecified sentences, LMs exhibit little uncertainty, contrary to what theoretical accounts of underspecification would predict. Overall, our study reveals limitations in current models' processing of sentence semantics and highlights the importance of using naturalistic data and communicative scenarios when evaluating LMs' language capabilities.
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。
