Fact-Preserved Personalized News Headline Generation

TL;DR

This paper introduces FPG, a framework for personalized news headline generation that balances user-specific relevance with factual accuracy, using fact-aware attention and contrastive learning.

Contribution

The paper proposes a novel framework FPG that improves factual consistency in personalized headlines by integrating fact-aware attention and contrastive learning.

Findings

FPG outperforms existing methods on the PENS benchmark.

FPG achieves a better tradeoff between personalization and factual accuracy.

Contrastive learning enhances factual consistency in generated headlines.

Abstract

Personalized news headline generation, aiming at generating user-specific headlines based on readers' preferences, burgeons a recent flourishing research direction. Existing studies generally inject a user interest embedding into an encoderdecoder headline generator to make the output personalized, while the factual consistency of headlines is inadequate to be verified. In this paper, we propose a framework Fact-Preserved Personalized News Headline Generation (short for FPG), to prompt a tradeoff between personalization and consistency. In FPG, the similarity between the candidate news to be exposed and the historical clicked news is used to give different levels of attention to key facts in the candidate news, and the similarity scores help to learn a fact-aware global user embedding. Besides, an additional training procedure based on contrastive learning is devised to further enhance the factual consistency of generated headlines. Extensive experiments conducted on a real-world benchmark PENS validate the superiority of FPG, especially on the tradeoff between personalization and factual consistency.