Scholarlink

<p>The Automatic identification of characters and their interactions from literary fiction is, arguably, a complex task that requires pipelines that leverage multiple Natural Language Processing (NLP) methods, such as Named Entity Recognition (NER) and Part-of-speech (POS) tagging. However, these methods are not optimized for retrieving Social Networks of Characters. Indeed, the currently available methods tend to underperform, especially in less-represented languages, due to a lack of manually annotated data for training. Here, we propose a pipeline, which we call Taggus, to extract social networks from literary fiction works in Portuguese without requiring a training phase. Our results show that compared to readily available State-of-the-Art tools—off-the-shelf NER tools and Large Language Models (ChatGPT)—the resulting pipeline, which uses POS tagging and a combination of heuristics, achieves satisfying results with an average F1-Score of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(92.1\%\)</EquationSource> </InlineEquation> in the task of identifying characters and solving for co-reference and <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(74.0\%\)</EquationSource> </InlineEquation> in interaction detection. These represent, respectively, increases of <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(115.7\%\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(38.1\%\)</EquationSource> </InlineEquation> over the results achieved by the readily available State-of-the-Art tools. Further steps to improve results are outlined, including methods for detecting relationships among characters. Limitations on the size and scope of our testing samples are acknowledged and in the exclusive focus on interactions as the relationship type. The Taggus pipeline is publicly available to encourage development in this field for the Portuguese language.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Taggus: an automated pipeline for the extraction of characters’ social networks from portuguese fiction literature

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月18日

查看全文
  • Tiago G. Canário,
  • Catarina Duarte,
  • Flávio L. Pinheiro,
  • João L. M. Pereira

摘要

The Automatic identification of characters and their interactions from literary fiction is, arguably, a complex task that requires pipelines that leverage multiple Natural Language Processing (NLP) methods, such as Named Entity Recognition (NER) and Part-of-speech (POS) tagging. However, these methods are not optimized for retrieving Social Networks of Characters. Indeed, the currently available methods tend to underperform, especially in less-represented languages, due to a lack of manually annotated data for training. Here, we propose a pipeline, which we call Taggus, to extract social networks from literary fiction works in Portuguese without requiring a training phase. Our results show that compared to readily available State-of-the-Art tools—off-the-shelf NER tools and Large Language Models (ChatGPT)—the resulting pipeline, which uses POS tagging and a combination of heuristics, achieves satisfying results with an average F1-Score of \(92.1\%\) in the task of identifying characters and solving for co-reference and \(74.0\%\) in interaction detection. These represent, respectively, increases of \(115.7\%\) and \(38.1\%\) over the results achieved by the readily available State-of-the-Art tools. Further steps to improve results are outlined, including methods for detecting relationships among characters. Limitations on the size and scope of our testing samples are acknowledged and in the exclusive focus on interactions as the relationship type. The Taggus pipeline is publicly available to encourage development in this field for the Portuguese language.