Human-like Natural Language Generation Using Monte Carlo Tree Search

Abstract

We propose a method of probabilistic natural language generation observing both a syntactic structure and an input of situational content. We employed Monte Carlo Tree Search for this nontrivial search problem, employing context-free grammar rules as search operators and evaluating numerous putative generations from these two aspects using logistic regression and n -gram language model. Through several experiments, we confirmed that our method can effectively generate sentences with various words and phrasings.