arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04941cs.CLcs.CY
收藏

从人道主义文档中提取定量信息

Quantitative Information Extraction from Humanitarian Documents

ISI Foundation(ISI基金会);Data Friendly Space

Daniele Liberatore, Kyriaki Kalimeri, Derya Sever, Yelena Mejova

AI总结:

本文构建人道主义领域定量信息抽取标注数据集,并提出定制 NLP 流水线,实现数量、单位、修饰语与相关事件的联合抽取,性能优于基线方法。

摘要:

人道主义行动伴随着大量报告、摘要、新闻和其他文档。为指导相关活动,必须从此类自由文本资源中快速提取重要信息。诸如受影响人数、已分发援助数量或基础设施受损程度等数量,对于应急响应和预期行动至关重要。在本工作中,我们贡献了一个面向人道主义领域的标注数据集,用于提取此类定量信息及其重要上下文,包括其所指的单位、任何修饰语以及相关事件。此外,我们开发了一个定制的 Natural Language Processing(自然语言处理)流水线,用于提取数量及其单位,并将其与基线方法和近期文献进行比较评估。所提出模型在性能上取得了稳定提升,尤其是在涉及多米尼加共和国和部分非洲国家的文档中。我们向研究社区公开数据集和代码,以持续改进人道主义领域的 NLP 工具。

英文摘要:

Humanitarian action is accompanied by a mass of reports, summaries, news, and other documents. To guide its activities, important information must be quickly extracted from such free-text resources. Quantities, such as the number of people affected, amount of aid distributed, or the extent of infrastructure damage, are central to emergency response and anticipatory action. In this work, we contribute an annotated dataset for the humanitarian domain for the extraction of such quantitative information, along side its important context, including units it refers to, any modifiers, and the relevant event. Further, we develop a custom Natural Language Processing pipeline to extract the quantities alongside their units, and evaluate it in comparison to baseline and recent literature. The proposed model achieves a consistent improvement in the performance, especially in the documents pertaining to the Dominican Republic and select African countries. We make the dataset and code available to the research community to continue the improvement of NLP tools for the humanitarian domain.

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。

↑