What is it about?
We propose a model that employs a pre-trained language model to increase the model's ability to understand question answering tasks. In addition, we develop a latent clustering method that analyses and uses topic information in the target dataset as additional information.
Featured Image
Photo by Nguyen Dang Hoang Nhu on Unsplash
Why is it important?
Our proposed latent clustering method is a model agnostic algorithm. It can be applied to any kind of neural network-based model.
Perspectives
I hope this article will give insight into people working on building AI models for question answering, dialogue systems, and topical clustering. This is a model-agnostic method. Try to add it to your model and see how it helps your model boost.
Seunghyun Yoon
Adobe Systems Inc
Read the Original
This page is a summary of: A Compare-Aggregate Model with Latent Clustering for Answer Selection, November 2019, ACM (Association for Computing Machinery),
DOI: 10.1145/3357384.3358148.
You can read the full text:
Resources
Contributors
The following have contributed to this page
