Discriminative Neural Sentence Modeling by Tree-Based Convolution

04/05/2015
by   Lili Mou, et al.
0

This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling. Our models leverage either constituency trees or dependency trees of sentences. The tree-based convolution process extracts sentences' structural features, and these features are aggregated by max pooling. Such architecture allows short propagation paths between the output layer and underlying feature detectors, which enables effective structural feature learning and extraction. We evaluate our models on two tasks: sentiment analysis and question classification. In both experiments, TBCNN outperforms previous state-of-the-art results, including existing neural networks and dedicated feature/rule engineering. We also make efforts to visualize the tree-based convolution process, shedding light on how our models work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/07/2015

Dependency-based Convolutional Neural Networks for Sentence Embedding

In sentence modeling and classification, convolutional neural network ap...
research
11/08/2016

Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents

The goal of sentence and document modeling is to accurately represent th...
research
01/07/2017

Structural Attention Neural Networks for improved sentiment analysis

We introduce a tree-structured attention neural network for sentences an...
research
05/21/2015

A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network

In this work, we address the problem to model all the nodes (words or ph...
research
12/28/2015

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

In this paper, we propose the TBCNN-pair model to recognize entailment a...
research
11/14/2018

A Grammar-Based Structural CNN Decoder for Code Generation

Code generation maps a program description to executable source code in ...
research
09/05/2021

Structural Optimization Makes Graph Classification Simpler and Better

In deep neural networks, better results can often be obtained by increas...

Please sign up or login with your details

Forgot password? Click here to reset