On the Identification of Suggestion Intents from Vietnamese Conversational Texts
Thi-Lan Ngo, Khac Linh Pham, Hideaki Takeda, Son Bao Pham, Xuan-Hieu Phan · 2017
Fully understanding suggestion intents in conversational texts is a complicated process that includes three major stages: user suggestion intents filtering, suggestion domain identification, and arguments extraction of suggestion intents. In the scope of this paper, we study the first phase, that is, building a binary classification model to determine whether a text unit carries suggestion intents or not. We come up with a new text unit to analysis suggestion based on functional segment in the ISO 24617-2 standard. We investigate two approaches to filter functional segments containing suggestion intents: machine learning using maximum entropy model and deep learning using convolutional neural networks model. The results of these experiments on Vietnamese online media texts are very promising. To the best of our knowledge, this is the first study to analyze suggestion at functional segment level.