Open AccessA Coherence Analysis Model for English Essay Based on Sentence Semantic Graph
Author(s) -
Guimin Huang,
Hui Tang,
Jiahao Wang,
Xuan Ye
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1693/1/012077
Subject(s) - coreference , computer science , semantic similarity , natural language processing , sentence , artificial intelligence , graph , information retrieval , theoretical computer science , resolution (logic)
Aiming at the problem that cannot be solved by the entity-based graph model, we propose a new discourse coherence quality analysis model (sentence semantic graph) by merging entity graph and semantic similarity graph of the text. Firstly, we use an improved coreference resolution module to process the coreference phenomenon in the text, and build a new type of entity graph with the processed results; secondly, we merge the entity graph and the semantic similarity based on the semantic space and get our sentence semantic graph lastly, we analyze the average outdegree of sentence semantic graph to indicate the degree of text coherence. Experiments show that this model is superior to the entity-based graph model and has a good effect on the automatic evaluation of English essay.