Improving Social Media Text Summarization by Learning Sentence Weight Distribution

TL;DR

This paper introduces a method for social media text summarization that learns sentence weight distribution to better focus on relevant information, reducing noise and improving summary quality.

Contribution

It proposes a novel approach using a multi-layer perceptron to predict sentence weights guided by ROUGE scores, enhancing relevance focus in summaries.

Findings

Outperforms baseline models on large social media datasets

Effectively reduces irrelevant noise in summaries

Improves ROUGE scores significantly

Abstract

Recently, encoder-decoder models are widely used in social media text summarization. However, these models sometimes select noise words in irrelevant sentences as part of a summary by error, thus declining the performance. In order to inhibit irrelevant sentences and focus on key information, we propose an effective approach by learning sentence weight distribution. In our model, we build a multi-layer perceptron to predict sentence weights. During training, we use the ROUGE score as an alternative to the estimated sentence weight, and try to minimize the gap between estimated weights and predicted weights. In this way, we encourage our model to focus on the key sentences, which have high relevance with the summary. Experimental results show that our approach outperforms baselines on a large-scale social media corpus.