作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2020, Vol. 46 ›› Issue (3): 40-45. doi: 10.19678/j.issn.1000-3428.0053393

• 人工智能与模式识别 • 上一篇    下一篇

基于BiLSTM模型的定义抽取方法

阳萍, 谢志鹏   

  1. 复旦大学 计算机科学技术学院, 上海 201203
  • 收稿日期:2018-12-13 修回日期:2019-03-22 发布日期:2019-04-28
  • 作者简介:阳萍(1994-),女,硕士研究生,主研方向为自然语言处理;谢志鹏,副教授、博士后。
  • 基金资助:
    国家重点研发计划(2018YFC0830900)。

Definition Extraction Method Based on BiLSTM Model

YANG Ping, XIE Zhipeng   

  1. School of Computer Science, Fudan University, Shanghai 201203, China
  • Received:2018-12-13 Revised:2019-03-22 Published:2019-04-28

摘要: 定义抽取是从非结构化文本中自动识别定义句的任务,定义抽取问题可建模为句子中术语及相应定义的序列标注问题,并利用标注结果完成抽取任务。针对传统的定义抽取方法在抽取定义特征过程中费时且容易造成错误传播的不足,提出一个基于双向长短时记忆(BiLSTM)的序列标注神经网络模型,对输入文本进行自动化定义抽取。通过将原始数据输入到BiLSTM神经网络中,完成输入句的特征表示,并采用基于LSTM的解码器进行解码得到标注结果。在Wikipedia英文数据集上的实验结果表明,该方法的精确率、召回率和F1值分别为94.21%、90.10%和92.11%,有效提升了基准模型效果。

关键词: 定义抽取, 双向长短时记忆模型, 序列标注, LSTM模型, 深度神经网络

Abstract: Definition extraction is the task that automatically identifying definition sentences from unstructured text.The definition extraction problem can be modeled as the sequence labeling problem of a sentence term and its corresponding definition,in which the extraction task can be accomplished by using the labeling results.Aiming at the shortcomings that the traditional definition extraction method can easily cause error propagation while defining features,this paper proposes a sequence labeling neural network model based on Bidirectional Long Short Term Memory(BiLSTM) to automatically execute definition extraction for input text.By inputting the original data into the BiLSTM neural network,this model completes the feature representation of the input sentences.Then,by using the LSTM based decoder for decoding,the labeling results are obtained.Experimental results on the Wikipedia English dataset show that the accuracy,recall and F1 value of the proposed method are 94.21%,90.10% and 92.11% respectively and it can effectively improve the effectiveness of the benchmark model.

Key words: definition extraction, Bidirectional Long Short Term Memory(BiLSTM) model, sequence labeling, LSTM model, Deep Neural Network(DNN)

中图分类号: