Detecting Contextomized Quotes in News Headlines by Contrastive Learning
This addresses the issue of misleading journalism for readers and fact-checkers, but it is incremental as it applies an existing contrastive learning method to a new domain-specific task.
The paper tackles the problem of detecting 'contextomized' quotes in news headlines, where quotes are used out of context to alter the speaker's intention, and presents QuoteCSE, a contrastive learning framework that achieves this detection with an F1-score of 0.85 on their dataset.
Quotes are critical for establishing credibility in news articles. A direct quote enclosed in quotation marks has a strong visual appeal and is a sign of a reliable citation. Unfortunately, this journalistic practice is not strictly followed, and a quote in the headline is often "contextomized." Such a quote uses words out of context in a way that alters the speaker's intention so that there is no semantically matching quote in the body text. We present QuoteCSE, a contrastive learning framework that represents the embedding of news quotes based on domain-driven positive and negative samples to identify such an editorial strategy. The dataset and code are available at https://github.com/ssu-humane/contextomized-quote-contrastive.