Header

UZH-Logo

Maintenance Infos

MuSeM: Detecting Incongruent News Headlines using Mutual Attentive Semantic Matching


Mishra, Rahul; Yadav, Piyush; Calizzano, Remi; Leippold, Markus (2020). MuSeM: Detecting Incongruent News Headlines using Mutual Attentive Semantic Matching. In: International Conference on Machine Learning and Applications (ICMLA) 2020, Miami, Florida, 14 December 2020 - 17 December 2020.

Abstract

Measuring 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.

Abstract

Measuring 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.

Statistics

Downloads

0 downloads since deposited on 19 Oct 2020
0 downloads since 12 months

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Banking and Finance
Dewey Decimal Classification:330 Economics
Language:English
Event End Date:17 December 2020
Deposited On:19 Oct 2020 08:06
Last Modified:19 Oct 2020 08:18
OA Status:Closed
Related URLs:https://www.icmla-conference.org/icmla20/ (Publisher)
Other Identification Number:merlin-id:19786

Download

Closed Access: Download allowed only for UZH members