Amharic Abstractive Text Summarization

TL;DR

This paper explores an innovative deep learning approach called Scheduled Sampling for abstractive text summarization, applied to Amharic, aiming to improve understanding and paraphrasing capabilities in low-resource languages.

Contribution

It introduces the application of curriculum learning with Scheduled Sampling to Amharic text summarization, enhancing NLP tools for African languages.

Findings

Demonstrates the effectiveness of Scheduled Sampling in Amharic summarization

Improves paraphrasing and contextual understanding in summaries

Contributes to African NLP community development

Abstract

Text Summarization is the task of condensing long text into just a handful of sentences. Many approaches have been proposed for this task, some of the very first were building statistical models (Extractive Methods) capable of selecting important words and copying them to the output, however these models lacked the ability to paraphrase sentences, as they simply select important words without actually understanding their contexts nor understanding their meaning, here comes the use of Deep Learning based architectures (Abstractive Methods), which effectively tries to understand the meaning of sentences to build meaningful summaries. In this work we discuss one of these new novel approaches which combines curriculum learning with Deep Learning, this model is called Scheduled Sampling. We apply this work to one of the most widely spoken African languages which is the Amharic Language, as we try to enrich the African NLP community with top-notch Deep Learning architectures.