Leveraging Syntactic Structures in Natural Language Processing

Abstract

Natural language processing (NLP) is a cross-discipline of computer science and linguistics. Significant improvements in deep learning algorithms and relevant models promote the advancement in the accuracy of language processing tasks. Deep learning participates as the linguistic character-extractor and learns through a deep neural network to handle greater data and facilitate achievements corresponding to the inputs. However, syntax-related ambiguities that cause uncertainty of outputs are often ignored. Therefore, this article will contrapose the ambiguous issues with discourse; it will introduce some basic syntactical study methods and information and then review the existing problems in natural language processing. Moreover, this work summarizes basic research and indicate prior knowledge of discourse ambiguities in natural language processing. Through the analyzing the distinctions in language processing and recent learning models, it is expected to present an explicit overview of relevant language subjects and potential research insights.