POSHAN: Cardinal POS Pattern Guided Attention for News Headline Incongruence

TL;DR

POSHAN is a neural attention model that effectively detects incongruent news headlines by focusing on cardinal POS patterns and phrase-guided attention, significantly improving performance on relevant datasets.

Contribution

The paper introduces a novel hierarchical attention network leveraging cardinal POS patterns and phrase-guided attention for better detection of headline incongruence.

Findings

Outperforms baseline methods on two datasets

Effective in highlighting cardinal values in headlines

Cardinal POS-pattern attention improves detection accuracy

Abstract

Automatic detection of click-bait and incongruent news headlines is crucial to maintaining the reliability of the Web and has raised much research attention. However, most existing methods perform poorly when news headlines contain contextually important cardinal values, such as a quantity or an amount. In this work, we focus on this particular case and propose a neural attention based solution, which uses a novel cardinal Part of Speech (POS) tag pattern based hierarchical attention network, namely POSHAN, to learn effective representations of sentences in a news article. In addition, we investigate a novel cardinal phrase guided attention, which uses word embeddings of the contextually-important cardinal value and neighbouring words. In the experiments conducted on two publicly available datasets, we observe that the proposed methodgives appropriate significance to cardinal values and outperforms all the baselines. An ablation study of POSHAN shows that the cardinal POS-tag pattern-based hierarchical attention is very effective for the cases in which headlines contain cardinal values.