arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.11560cs.CL
收藏

自然语言处理任务在自动构建文学人物网络中的作用

The Role of Natural Language Processing Tasks in Automatic Literary Character Network Construction

Laboratoire Informatique d’Avignon(阿维尼翁计算机实验室);Laboratoire des Sciences du Numérique de Nantes(南特数字科学实验室)

Arthur Amalvy, Vincent Labatut, Richard Dufour

AI总结:

本研究首次系统评估NLP级联流水线中命名实体识别与共指消解对文学人物网络构建的影响,通过误差注入实验证明共指消解对召回率的关键作用,并指出传统流水线在召回率上优于大型语言模型方法。

摘要:

从文学文本中自动提取人物网络通常采用自然语言处理(NLP)级联流水线。尽管这种方法广泛使用,但尚无研究探讨低级NLP任务对其性能的影响。本文在文学数据集上进行了此类研究,重点关注命名实体识别(NER)和共指消解在提取共现网络中的作用。为了突出这些任务性能的影响,我们从黄金标准标注出发,逐步添加均匀分布的误差,并观察它们对人物网络质量的影响。我们证明,NER性能取决于所测试的小说,并强烈影响人物检测。我们还表明,仅靠NER检测到的提及会遗漏大量人物共现,而共指消解对于防止这种情况是必要的。最后,我们提供了与2种基于大型语言模型(LLM)的方法(包括一种完全端到端的方法)的比较点,并表明这些模型在召回率方面不如传统NLP流水线。

英文摘要:

The automatic extraction of character networks from literary texts is generally carried out using natural language processing (NLP) cascading pipelines. While this approach is widespread, no study exists on the impact of low-level NLP tasks on their performance. In this article, we conduct such a study on a literary dataset, focusing on the role of named entity recognition (NER) and coreference resolution when extracting co-occurrence networks. To highlight the impact of these tasks' performance, we start with gold-standard annotations, progressively add uniformly distributed errors, and observe their impact in terms of character network quality. We demonstrate that NER performance depends on the tested novel and strongly affects character detection. We also show that NER-detected mentions alone miss a lot of character co-occurrences, and that coreference resolution is needed to prevent this. Finally, we present comparison points with 2 methods based on large language models (LLMs), including a fully end-to-end one, and show that these models are outperformed by traditional NLP pipelines in terms of recall.

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。

↑