区分虚构人物声音：面向引语归属的作者验证模型研究
Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution
AI总结：
针对现有直接引语说话者检测依赖局部语境信息的问题，本研究用预训练作者验证模型在小说语料库构建人物风格表征，发现风格加主题信息可区分人物但未提升引语归属效果，且结果因作品而异，需适配文学文本的文体模型。
摘要：
当前自动检测直接引语说话者的方法往往忽略人物的整体信息，转而依赖语境中的局部信息，比如上下文提及的实体。本研究在大型英语小说语料库Project Dialogism Novel Corpus（对话主义项目小说语料库）中，利用现成的预训练Authorship Verification（作者验证）模型对人物引语进行编码，探究构建出的人物风格表征。结果表明，部分此类模型捕捉到的风格与主题信息结合后，可准确区分不同人物，但在引语归属任务上未必优于仅用语义的模型。不过，这些结果因小说而异，还需进一步研究专门适配文学文本与人物研究的文体计量模型。
英文摘要：
Recent approaches to automatically detect the speaker of an utterance of direct speech often disregard general information about characters in favor of local information found in the context, such as surrounding mentions of entities. In this work, we explore stylistic representations of characters built by encoding their quotes with off-the-shelf pretrained Authorship Verification models in a large corpus of English novels (the Project Dialogism Novel Corpus). Results suggest that the combination of stylistic and topical information captured in some of these models accurately distinguish characters among each other, but does not necessarily improve over semantic-only models when attributing quotes. However, these results vary across novels and more investigation of stylometric models particularly tailored for literary texts and the study of characters should be conducted.
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。
