Kyo-Joong Oh  Dongkun Lee  Chae-Gyun Lim  Ho-Jin Choi

10.5626/JOK.2019.46.9.909

Natural Language Understanding sentence embedding automatic feature extraction question similarity analysis

This paper describes a method for the automatic extraction of feature vectors that can be used to analyze the similarity among natural language sentences. Similarity analysis among sentences is a necessary aspect of measuring semantic or structural similarity in natural language understanding. The analysis results can be used to find answers in Question and Answer (Q&A) systems and dialogue systems. The similarity analysis uses sentence vectors extracted by two deep learning models: the Recurrent Neural Network (RNN) to reflect sequential information of expressions such as syllables and semantic morphemes, and the Convolutional Neural Network (CNN) for characterizing the appearance patterns of similar expressions such as words or phrases. In this paper, we examine the accuracy and quality of the method using sentence vectors that are automatically extracted by the models from dialogues related to banking service. This method can find more similar questions and answers in FAQs than existing methods. The automatic feature extraction method can be used to analyze the similarity of Korean sentences across various application domains and systems.