DEF Generation for Terminologies Based on Tree-structured Decoder
This paper investigates the automatic generation of DEF based on KDML of HowNet,and proposes a gen-eration method based on tree-structured decoder.The inputs of the encoder are technical terms and other external in-formation(definition of the terms,sememes of sub-words of the terms,etc.).As for decoding,sememe decoder and role decoder are used alternately,and attention mechanism is used to capture various representation information.Finally,the output in the form of"sememe-role-sememe"is obtained,which is combined into the sememe tree cor-responding to terms to finalize the DEF representation of terms in HowNet.Experimental results show that the pro-posed method achieves 74.13％F1-value for the first sememe generation,53.92％for the overall sememe genera-tion,53.33％for the role generation and 30.48％for the overall triple generation.
万方数据
维普
