arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.12293cs.CL
收藏

使用异质知识表示的文本和作者级政治推理

Text and author-level political inference using heterogeneous knowledge representations

University of São Paulo(圣保罗大学)

Samuel Caetano da Silva, Ivandre Paraboni

摘要:

从文本数据中推断政治信息是自然语言处理(NLP)在文本和作者级别上的热门研究课题。近年来,这类研究已经实施与援助的表示从Transformers,如BERT。尽管取得了相当大的成功,但是,我们可能会问,是否可以通过将基于转换的模型与附加的知识表示相结合来进一步改进结果。为了阐明这个问题,目前的工作描述了一系列的实验,比较替代模型配置的政治推理,从文本中的英语和葡萄牙语。结果表明,某些文本表示-特别是结合使用BERT预训练的语言模型与句法依赖模型-可能会在多个实验设置中优于替代方案,为进一步研究在这些和其他可能的NLP任务中使用异构文本表示提供了潜在的强有力的理由。

英文摘要:

The inference of politically-charged information from text data is a popular research topic in Natural Language Processing (NLP) at both text- and author-level. In recent years, studies of this kind have been implemented with the aid of representations from transformers such as BERT. Despite considerable success, however, we may ask whether results may be improved even further by combining transformed-based models with additional knowledge representations. To shed light on this issue, the present work describes a series of experiments to compare alternative model configurations for political inference from text in both English and Portuguese languages. Results suggest that certain text representations - in particular, the combined use of BERT pre-trained language models with a syntactic dependency model - may outperform the alternatives across multiple experimental settings, making a potentially strong case for further research in the use of heterogeneous text representations in these and possibly other NLP tasks.

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。

↑