Coreference Resolution Using Semantic Features and Fully Connected Neural Network in the Persian Language

Abstract

Coreference resolution is one of the most critical issues in various applications of natural language processing, such as machine translation, sentiment analysis, summarization, etc. In the process of coreference resolution, in this paper, a fully connected neural network approach has been adopted to enhance the performance of feature extraction whilst also facilitating the mention pair classification process for coreference resolution in the Persian language. For this purpose, first, we focus on the feature extraction phase by fusing some handcrafted features, word embedding features and semantic features. Then, a fully connected deep neural network is utilized to determine the probability of the validity of the mention pairs. After that, the numeric output of the last layer of the utilized neural network is considered as the feature vector of the valid mention pairs. Finally, the coreference mention pairs are specified by utilizing a hierarchical accumulative clustering method. The proposed method's evaluation on the Uppsala dataset demonstrates a meaningful improvement, as indicated by the F-score 64.54%, in comparison to state-of-the-art methods.

Keywords

• Coreference resolution
• Fully connected neural networks
• Deep learning
• Hierarchical accumulative clustering
• Persian language