Bengali Abstractive News Summarization(BANS): A Neural Attention Approach

TL;DR

This paper introduces a Bengali abstractive news summarization system using a seq2seq LSTM model with attention, trained on a large dataset, achieving significant improvements over previous methods.

Contribution

The paper presents the first large-scale Bengali news summarization dataset and a novel attention-based seq2seq LSTM model that outperforms existing approaches.

Findings

Significant improvement in human evaluation scores.

Largest publicly available Bengali news summarization dataset.

Effective attention mechanism producing human-like summaries.

Abstract

Abstractive summarization is the process of generating novel sentences based on the information extracted from the original text document while retaining the context. Due to abstractive summarization's underlying complexities, most of the past research work has been done on the extractive summarization approach. Nevertheless, with the triumph of the sequence-to-sequence (seq2seq) model, abstractive summarization becomes more viable. Although a significant number of notable research has been done in the English language based on abstractive summarization, only a couple of works have been done on Bengali abstractive news summarization (BANS). In this article, we presented a seq2seq based Long Short-Term Memory (LSTM) network model with attention at encoder-decoder. Our proposed system deploys a local attention-based model that produces a long sequence of words with lucid and human-like generated sentences with noteworthy information of the original document. We also prepared a dataset of more than 19k articles and corresponding human-written summaries collected from bangla.bdnews24.com1 which is till now the most extensive dataset for Bengali news document summarization and publicly published in Kaggle2. We evaluated our model qualitatively and quantitatively and compared it with other published results. It showed significant improvement in terms of human evaluation scores with state-of-the-art approaches for BANS.