Description Based Text Classification with Reinforcement Learning

02/08/2020
by   Duo Chai, et al.
0

The task of text classification is usually divided into two stages: text feature extraction and classification. In this standard formalization categories are merely represented as indexes in the label vocabulary, and the model lacks for explicit instructions on what to classify. Inspired by the current trend of formalizing NLP problems as question answering tasks, we propose a new framework for text classification, in which each category label is associated with a category description. Descriptions are generated by hand-crafted templates or using abstractive/extractive models from reinforcement learning. The concatenation of the description and the text is fed to the classifier to decide whether or not the current label should be assigned to the text. The proposed strategy forces the model to attend to the most salient texts with respect to the label, which can be regarded as a hard version of attention, leading to better performances. We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

04/06/2020

Joint Embedding of Words and Category Labels for Hierarchical Multi-label Text Classification

Text classification has become increasingly challenging due to the conti...
12/08/2020

Unsupervised Label Refinement Improves Dataless Text Classification

Dataless text classification is capable of classifying documents into pr...
04/06/2020

Deep Learning Based Text Classification: A Comprehensive Review

Deep learning based models have surpassed classical machine learning bas...
04/02/2022

Constrained Sequence-to-Tree Generation for Hierarchical Text Classification

Hierarchical Text Classification (HTC) is a challenging task where a doc...
09/01/2019

Topics to Avoid: Demoting Latent Confounds in Text Classification

Despite impressive performance on many text classification tasks, deep n...
10/07/2020

Multi-label classification of promotions in digital leaflets using textual and visual information

Product descriptions in e-commerce platforms contain detailed and valuab...
07/07/2011

Text Classification: A Sequential Reading Approach

We propose to model the text classification process as a sequential deci...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.