MuSeM: Detecting Incongruent News Headlines using Mutual Attentive Semantic Matching
This addresses the issue of deceptive and misleading news headlines on the web, which is an incremental improvement over existing text similarity and attention-based approaches.
The paper tackles the problem of detecting incongruent news headlines by proposing a method that uses mutual attentive semantic matching between original and synthetically generated headlines, achieving significant performance improvements over prior methods on two public datasets.
Measuring the congruence between two texts has several useful applications, such as detecting the prevalent deceptive and misleading news headlines on the web. Many works have proposed machine learning based solutions such as text similarity between the headline and body text to detect the incongruence. Text similarity based methods fail to perform well due to different inherent challenges such as relative length mismatch between the news headline and its body content and non-overlapping vocabulary. On the other hand, more recent works that use headline guided attention to learn a headline derived contextual representation of the news body also result in convoluting overall representation due to the news body's lengthiness. This paper proposes a method that uses inter-mutual attention-based semantic matching between the original and synthetically generated headlines, which utilizes the difference between all pairs of word embeddings of words involved. The paper also investigates two more variations of our method, which use concatenation and dot-products of word embeddings of the words of original and synthetic headlines. We observe that the proposed method outperforms prior arts significantly for two publicly available datasets.