Adaptive Multi-Compositionality for Recursive Neural Network Models

doi:10.1109/TASLP.2015.2509257

Adaptive Multi-Compositionality for Recursive Neural Network Models

2016-03-01

21

PRE

AI

DOI：10.1109/TASLP.2015.2509257

Original

Original request for help

Save

Abstract

En 中文

Recursive neural network models have achieved promising results in many natural language processing tasks. The main difference among these models lies in the composition function, i.e., how to obtain the vector representation for a phrase or sentence using the representations of words it contains. This paper introduces a novel Adaptive Multi-Compositionality (AdaMC) layer to recursive neural network models. The basic idea is to use more than one composition function and adaptively select them depending on input vectors. We develop a general framework to model the semantic composition as a distribution of these composition functions. The composition functions and parameters used for adaptive selection are jointly learnt from the supervision of specific tasks. We integrate AdaMC into existing recursive neural network models and conduct extensive experiments on the Stanford Sentiment Treebank and semantic relation classification task. The experimental results demonstrate that AdaMC improves the performance of recursive neural network models and outperforms the baseline methods.

Keywords:

Compositionality

neural network

recursive neural network (RNN)

semantic composition

Adaptive Multi-Compositionality for Recursive Neural Network Models

Abstract

AI Summary

Journal

Organization