Application of the Multi-label Residual Convolutional Neural Network text classifier using Content-Based Routing process

TL;DR

This paper presents a multi-label residual CNN approach for classifying legal ads based on their text, utilizing a content-based routing process to improve NLP-based classification accuracy.

Contribution

It introduces a novel multi-label residual CNN model combined with content-based routing for legal ad text classification, addressing specific challenges in supervised NLP tasks.

Findings

Effective classification of legal ads achieved

Improved accuracy over traditional models demonstrated

Content-based routing enhances model performance

Abstract

In this article, we will present an NLP application in text classifying process using the content-based router. The ultimate goal throughout this article is to predict the event described by a legal ad from the plain text of the ad. This problem is purely a supervised problem that will involve the use of NLP techniques and conventional modeling methodologies through the use of the Multi-label Residual Convolutional Neural Network for text classification. We will explain the approach put in place to solve the problem of classified ads, the difficulties encountered and the experimental results.