Multi-Label Text Classification using Attention-Based Graph Neural Network

Improving Natural Language Processing

Multi-Label Text Classification (MLTC), through which one or more labels are assigned to each input sample, is essential for effective Natural Language Processing (NLP). However, most MLTC tasks include dependencies or correlations among labels that traditional classification methods overlook.

This paper shows how an attention-based graph neural network can capture these dependencies for better results. Validation across five real-world MLTC datasets reveals that the proposed model achieves consistently higher accuracy than conventional approaches.

Ankit Pal, Muru Selvakumar, and Malaikannan Sankarasubbu conducted this research for the Saama AI Research team.

Download Paper
First Name
Last Name
Email*
Phone
Job Title
Company Name
- I agree to receive other communications from Saama.
Saama is committed to protecting and respecting your privacy, and we’ll only use your personal information to administer your account and to provide the products and services you requested from us. Separately, from time to time, we would like to contact you about our products and services, as well as other content that may be of interest to you. If you consent to us contacting you for this purpose, please tick the checkbox authorizing us to contact you at the email address above.
*
- I agree to allow Saama to process and store my personal data.
In order to provide you with the content requested, we need to process and store your personal data. If you consent to our storing your personal data for this purpose, please tick the checkbox.
You may unsubscribe from these communications at any time. For more information on how to unsubscribe, our privacy practices, and how we are committed to protecting and respecting your privacy, please review our Privacy Policy.

Multi-Label Text Classification using Attention-Based Graph Neural Network

Download Paper