Lifelong Learning Maxent for Suggestion Classification

Resumen

Suggestion classification for opinion data is defined as identifying a given utterance by suggestionor non-suggestion class. In this paper, we introduce a method called LLMaxent which is the solution for thecross-domain suggestion classification. LLMaxent isa life long machine learning approach using maximu mentropy (Maxent). In the course of life long learning, the drawn knowledge from the past tasks is retained and supported for the future learning. From that,we build a classifier by using labeled data in existed domains for suggestion classification in a new domain. The experimental results show that the proposed novel model can improve the performance of cross-domain suggestion classification. This is one of the preliminary research in lifelong machine learning using Maxent. Its effect is not only for suggestion classification but also forcross-domain text classification in general.