Anaphoricity Determination of Anaphora Resolution in Uygur Pronoun Based on CNN-LSTM Model
Anaphoricity Determination of Anaphora Resolution in Uygur Pronoun Based on CNN-LSTM Model
复制标题
DOI：
10.1142/s146902681750016x
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
Shengwei Tian;Dongbai Li;Long Yu;Guanjun Feng;Jianguo Zhao;Liuqing Pu
中科院分区：
文献类型：
--
作者：
Shengwei Tian;Dongbai Li;Long Yu;Guanjun Feng;Jianguo Zhao;Liuqing Pu
作为回指消解的核心子任务，回指确定引起了研究者的广泛关注。然而，在最近的研究中，深层语义信息和共指元素的上下文所造成的影响并没有被考虑在内。本文结合维吾尔语的语义特征，建立了维吾尔语代词回指的卷积神经网络&长短期记忆（CNN_LSTM）模型。首先，通过word2vec提取深度否定语义特征表示；其次，提取共参元素的浅层显式特征表示；然后结合两种特征来识别共指元素是否具有指称性。结果表明，该方法能够准确地识别出共参考元素，ACC+得分为90.18%，ACC−得分为89.93%，分别高于人工神经网络（ANN）和支持向量机（SVM）。
As a core subtask in anaphora resolution, anaphoricity determination has aroused the interest of researchers. However, in recent work, the influence caused by the deep semantic information and the context of the coreference elements have not been taken into account. In this paper, by combining the semantic feature of Uygur, we established a Convolutional Neural Network & Long Short-Term Memory (CNN_LSTM) model in determining the anaphoricity of Uygur pronoun. Firstly, the deep negative semantic feature representation is extracted via word2vec. Secondly, the shallow explicit feature representation of coreference elements is extracted by our system. Afterwards, two kinds of features are combined to recognize whether coreference element is referential or not. The results showed that the method we used can distinguish coreference element accurately, the ACC+ score is 90.18% and the ACC− score is 89.93%, which are higher than ANN (Artificial Neural Network) and SVM (Support Vector Machine) respectively.