Human-like Natural Language Generation Using Monte Carlo Tree Search

By Kaori Kumagai, Ichiro Kobayashi, Daichi Mochihashi, Hideki Asoh, Tomoaki Nakamura, T. Nagai. 2016

19 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, methodology): “Put another way, one can easily maximize a metric by employing methods like ranking all utterances according to a learned metric, or using Monte Carlo Tree Search (Kumagai et al., 2016) during generation to naı̈vely optimize the automatic metric.”
Generating Fluent Adversarial Examples for Natural Languages (2019, background): “tasks, such as natural language generation (Kumagai et al., 2016), constrained sentence generation (Miao et al.”