Rationale-Augmented Convolutional Neural Networks for Text Classification

05/14/2016
by   Ye Zhang, et al.
0

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or snippets) that support their overall document categorization, i.e., they provide rationales. Our model exploits such supervision via a hierarchical approach in which each document is represented by a linear combination of the vector representations of its component sentences. We propose a sentence-level convolutional model that estimates the probability that a given sentence is a rationale, and we then scale the contribution of each sentence to the aggregate document representation in proportion to these estimates. Experiments on five classification datasets that have document labels and associated rationales demonstrate that our approach consistently outperforms strong baselines. Moreover, our model naturally provides explanations for its predictions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2023

SLCNN: Sentence-Level Convolutional Neural Network for Text Classification

Text classification is a fundamental task in natural language processing...
research
05/31/2020

Improve Document Embedding for Text Categorization Through Deep Siamese Neural Network

Due to the increasing amount of data on the internet, finding a highly-i...
research
04/04/2023

MEGClass: Text Classification with Extremely Weak Supervision via Mutually-Enhancing Text Granularities

Text classification typically requires a substantial amount of human-ann...
research
10/15/2020

Neural Deepfake Detection with Factual Structure of Text

Deepfake detection, the task of automatically discriminating machine-gen...
research
08/31/2018

A Deep Neural Network Sentence Level Classification Method with Context Information

In the sentence classification task, context formed from sentences adjac...
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
06/27/2021

Deep Learning for Technical Document Classification

In large technology companies, the requirements for managing and organiz...

Please sign up or login with your details

Forgot password? Click here to reset