汉语否定焦点识别研究:数据集与基线系统(Research on Chinese Negative Focus Identification: Dataset and Baseline)

Jiaxuan Sheng (盛佳璇), Bowei Zou (邹博伟), Longxiang Shen (沈龙骧), Jing Ye (叶静), Yu Hong (洪宇)


Abstract
自然语言文本中存在大量否定语义表达,否定焦点识别任务作为更细粒度的否定语义分析,近年来开始受到自然语言处理学者的关注。该任务旨在识别句子中被否定词修饰和强调的文本片段,其对自然语言处理的下游任务,如情感分析、观点挖掘等具有重要意义。与英语相比,目前面向汉语的否定焦点识别研究彶展缓慢,其主要原因是尚未有中文数据集为模型提供训练和测试数据。为解决上述问题,本文在汉语否定与不确定语料库上进行了否定焦点的标注工作,初步探索了否定焦点在汉语上的语言现象,并构建了一个包含5,762个样本的数据集。同时,本文还提出了一个基于神经网络模型的基线系统,为后续相关研究提供参照。
Anthology ID:
2020.ccl-1.51
Volume:
Proceedings of the 19th Chinese National Conference on Computational Linguistics
Month:
October
Year:
2020
Address:
Haikou, China
Editors:
Maosong Sun (孙茂松), Sujian Li (李素建), Yue Zhang (张岳), Yang Liu (刘洋)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
550–560
Language:
Chinese
URL:
https://aclanthology.org/2020.ccl-1.51
DOI:
Bibkey:
Cite (ACL):
Jiaxuan Sheng, Bowei Zou, Longxiang Shen, Jing Ye, and Yu Hong. 2020. 汉语否定焦点识别研究:数据集与基线系统(Research on Chinese Negative Focus Identification: Dataset and Baseline). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 550–560, Haikou, China. Chinese Information Processing Society of China.
Cite (Informal):
汉语否定焦点识别研究:数据集与基线系统(Research on Chinese Negative Focus Identification: Dataset and Baseline) (Sheng et al., CCL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.ccl-1.51.pdf