Dynamic Compositional Neural Networks over Tree Structure

05/11/2017
by   Pengfei Liu, et al.
0

Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information. In spite of their success, most existing models suffer from the underfitting problem: they recursively use the same shared compositional function throughout the whole compositional process and lack expressive power due to inability to capture the richness of compositionality. In this paper, we address this issue by introducing the dynamic compositional neural networks over tree structure (DC-TreeNN), in which the compositional function is dynamically generated by a meta network. The role of meta-network is to capture the metaknowledge across the different compositional rules and formulate them. Experimental results on two typical tasks show the effectiveness of the proposed models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2018

Learning to Compose over Tree Structures via POS Tags

Recursive Neural Network (RecNN), a type of models which compose words o...
research
02/25/2018

Meta Multi-Task Learning for Sequence Modeling

Semantic composition functions have been playing a pivotal role in neura...
research
02/13/2020

A Framework for End-to-End Learning on Semantic Tree-Structured Data

While learning models are typically studied for inputs in the form of a ...
research
10/26/2022

Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation

Since batch algorithms suffer from lack of proficiency in confronting mo...
research
09/13/2016

Towards Deep Compositional Networks

Hierarchical feature learning based on convolutional neural networks (CN...
research
01/31/2023

Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality

A recent line of work in NLP focuses on the (dis)ability of models to ge...
research
05/19/2021

Compositional Processing Emerges in Neural Networks Solving Math Problems

A longstanding question in cognitive science concerns the learning mecha...

Please sign up or login with your details

Forgot password? Click here to reset