A deep neural network model for coreference resolution in geological domain. Issue 3 (May 2023)

• Record Type: Journal Article
• Authors: Wan, Bo; Dong, Shuai; Chu, Deping; Li, Hong; Liu, Yiyang; Fu, Jinming; Fang, Fang; Li, Shengwen; Zhou, Dan
• Is Part Of: Information processing & management. Volume 60:Issue 3(2023)
• Publication Date: 2023-05
• Subjects: Geological text mining -- Coreference resolution -- Deeping learning -- Chinese geological texts; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2023.103268
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: The coreference resolution of geological entities in the geological domain is explored for the first time. A novel framework for geological entity coreference resolution based on deep learning methods is proposed. A CNN-based multi-scale structure feature extraction module for geological terms is designed. A state-of-the-art coreference resolution performance for geological entities is reported. Abstract: Coreference resolution of geological entities is an important task in geological information mining. Although the existing generic coreference resolution models can handle geological texts, a dramatic decline in their performance can occur without sufficient domain knowledge. Due to the high diversity of geological terminology, coreference is intricately governed by the semantic and expressive structure of geological terms. In this paper, a framework CorefRoCNN based on RoBERTa and convolutional neural network (CNN) for end-to-end coreference resolution of geological entities is proposed. Firstly, the fine-tuned RoBERTa language model is used to transform words into dynamic vector representations with contextual semantic information. Second, a CNN-based multi-scale structure feature extraction module for geological terms is designed to capture the invariance of geological terms in length, internal structure, and distribution. Thirdly, we incorporate the structural feature and word embedding for further determinations of coreference relations. In addition, attention mechanisms are used to improve the ability of the model to capture valid information in geological texts with long sentence lengths. To validate the effectiveness of the model, we compared it with several state-of-the-art models on the constructed dataset. The results show that our model has the optimal performance with an average F1 value of 79.78%, which is a 1.22% improvement compared to the second-ranked method.