Fusing Word Semantics and Label Dependence for Implicit Discourse Relation Recognition
Chinese implicit discourse relationship recognition aims to infer the type of discourse relationship between two arguements.Howev-er,the existing methods often ignore the key information contained in the words in the argument,and only consider the types of discourse rela-tionships within a single level,and ignore the dependent relationship between levels.Therefore,this paper proposes a method that integrates word semantics and label dependence to realize discourse relationship recognition by sequence generation.Firstly,the word vector is embed-ded in the character encoding representation according to the similarity weight,and the word alignment attention mechanism is applied to em-phasize the keywords and word information.Then,label attention coding is used to obtain the contextual representation of discourse relation-ship dependence from the meta-representation and discourse relationship representation containing word semantics,and predict the top-level discourse relationship type in a bottom-up manner.In addition,this paper constructs a discourse relationship dataset for reading comprehen-sion discourses,and experiments are carried out on this dataset,and the results show that the accuracy rate and F1 value of implicit discourse relationship recognition reach 74.19%and 73.81%,which finally verifies the effectiveness of the proposed method.
万方数据
维普
