MTL-KIGN

Summary

We propose a key information guide network for abstractive text summarization based on a multi-task learning framework. The core idea is to automatically extract the key information that people need most in an end-to-end way and use it to guide the generation process, so as to get a more human-compliant summary. In our model, the document is encoded into two parts: results of the normal document encoder and the key information encoding, and the key information includes the key sentences and the keywords. A multi-task learning framework is introduced to get a more sophisticated end-to-end model. To fuse the key information, we propose a novel multi-view attention guide network to obtain the dynamic representations of the source text and the key information. In addition, the dynamic representations are incorporated into the abstraction module to guide the process of summary generation.

Architecture

Experiments

Performance

Further Readings

A Primer on Multi-task Learning - Part 1

Towards building a " Generalist " model Multi-task Learning (MTL) is a collection of techniques intended to learn multiple tasks simultaneously instead of learning them separately. The motivation behind MTL is to create a " Generalist" model that can solve multiple tasks rather than creating multiple " Specialist" models that are trained to solve only one task.

https://medium.com/analytics-vidhya/a-primer-on-multi-task-learning-in-nlp-part-1-7154b4227c0e