自编码
计算机科学
树(集合论)
人工智能
编码器
解析
语法
深度学习
语法归纳法
机器学习
解析树
时间复杂性
循环神经网络
人工神经网络
基于规则的机器翻译
模式识别(心理学)
算法
数学
哲学
数学分析
操作系统
语言学
作者
Benjamin Paaßen,Irena Koprinska,Kalina Yacef
出处
期刊:Machine Learning
[Springer Nature]
日期:2022-08-02
卷期号:111 (9): 3393-3423
被引量:3
标识
DOI:10.1007/s10994-022-06223-7
摘要
Abstract Machine learning on trees has been mostly focused on trees as input. Much less research has investigated trees as output, which has many applications, such as molecule optimization for drug discovery, or hint generation for intelligent tutoring systems. In this work, we propose a novel autoencoder approach, called recursive tree grammar autoencoder (RTG-AE), which encodes trees via a bottom-up parser and decodes trees via a tree grammar, both learned via recursive neural networks that minimize the variational autoencoder loss. The resulting encoder and decoder can then be utilized in subsequent tasks, such as optimization and time series prediction. RTG-AEs are the first model to combine three features: recursive processing, grammatical knowledge, and deep learning. Our key message is that this unique combination of all three features outperforms models which combine any two of the three. Experimentally, we show that RTG-AE improves the autoencoding error, training time, and optimization score on synthetic as well as real datasets compared to four baselines. We further prove that RTG-AEs parse and generate trees in linear time and are expressive enough to handle all regular tree grammars.
科研通智能强力驱动
Strongly Powered by AbleSci AI