摘要
提出一种自解释句子抽取框架(Extra-iNet),该框架仅依赖于粗粒度的任务级标签,从输入文档中抽取部分句子,指导文档标签的预测,并为预测结果提供人类可读的解释。该框架利用卷积神经网络编码输入句子,将预测解释性句子的抽取和表征整合在同一模块,采用强化学习和门控机制2种策略抽取解释子集,并由此推导出Hard Extra-iNet和Soft Extra-iNet 2种变体模型。分别在情感分析任务和累计超额收益预测任务上对模型的预测能力和解释能力进行验证。研究结果表明:相比于基线,模型在情感分析任务上的F1(精度与召回率的调和平均数)平均提高了15.5%,在累计超额收益预测任务上的准确率平均提高了3.7%;模型抽取的结果与人类标注的结果高度一致。Extra-iNet框架可以有效地从文档中抽取解释性句子,可推广应用于不同领域的文本预测任务。
A self-explanatory sentence extraction framework(Extra-iNet)was proposed,which relied solely on coarse-grained task-level labels to extract certain sentences from input documents to guide document label prediction and provide human-readable explanations for the prediction results. This framework utilized a convolutional neural network to encode input sentences, and integrated the extraction and representation of predictive explanatory sentences into a single module. Reinforcement learning and gating mechanisms were adopted as two strategies to extract the explanatory subset, resulting in two variant models, namely Hard Extra iNet and Soft Extra-iNet. The predictive and explanatory capabilities of the models were validated on sentiment analysis task and cumulative abnormal return prediction task. The results show that, compared to the baselines, the model's F1 (the harmonic mean of precision and recall) in sentiment analysis task increases by an average of 15.5%, and its accuracy in cumulative abnormal return prediction task increases by an average of 3.7%. The results extracted by the model are highly consistent with the results annotated by humans. Extra-iNet framework can effectively extract explanatory sentences from documents and can be applied to the prediction in other fields.
作者
段俊文
贾智豪
蒋晗
丁效
仲文明
DUAN Junwen;JIA Zhihao;JIANG Han;DING Xiao;ZHONG Wenming(School of Computer Science and Engineering,Central South University,Changsha 410083,China;Faculty of Computing,Harbin Institute of Technology,Harbin 150001,China;School of Foreign Languages,Central South University,Changsha 410083,China)
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2024年第9期3342-3353,共12页
Journal of Central South University:Science and Technology
基金
国家社会科学基金资助项目(21BYY086)
国家自然科学青年基金资助项目(62006251)
中南大学前沿交叉研究项目(2023QYJC023)。
关键词
可解释预测
强化学习
深度神经网络
情感分析
累积超额收益
interpretable prediction
reinforcement learning
deep neural network
sentiment analysis
cumulative abnormal return
