Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fact-Preserved Personalized News Headline Generation

Zhao Yang, Junhong Lian, Xiang Ao

TL;DR

The paper tackles the challenge of generating personalized news headlines while preserving factual accuracy. It introduces FPG, a Transformer-based framework with a history encoder, a personalized news encoder, and a user-guided decoder, augmented by a contrastive-learning-based objective to enhance factual consistency. A fact-aware global user embedding and history-informed attention guide headline generation to align with user interests without sacrificing fidelity to source content. On the PENS benchmark, FPG demonstrates a favorable balance between personalization and factuality, outperforming baselines in ROUGE-based coverage and FactCC evaluation, with illustrative cases showing improved alignment to individual readers' preferences.

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.

Fact-Preserved Personalized News Headline Generation

TL;DR

The paper tackles the challenge of generating personalized news headlines while preserving factual accuracy. It introduces FPG, a Transformer-based framework with a history encoder, a personalized news encoder, and a user-guided decoder, augmented by a contrastive-learning-based objective to enhance factual consistency. A fact-aware global user embedding and history-informed attention guide headline generation to align with user interests without sacrificing fidelity to source content. On the PENS benchmark, FPG demonstrates a favorable balance between personalization and factuality, outperforming baselines in ROUGE-based coverage and FactCC evaluation, with illustrative cases showing improved alignment to individual readers' preferences.

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.
Paper Structure (20 sections, 9 equations, 2 figures, 3 tables, 1 algorithm)

This paper contains 20 sections, 9 equations, 2 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Methodology
  5. History Encoder
  6. Personalized News Encoder
  7. User-guided Decoder
  8. Fact-enhanced Training
  9. Experiment Settings
  10. Datasets Settings
  11. Baselines
  12. Evaluation Metrics
  13. Personalization
  14. Factual Consistency
  15. Coverage
  16. ...and 5 more sections

Figures (2)

  • Figure 1: An example illustrating the personalization in news headlines.
  • Figure 2: The framework of FPG. It has N layers of transformer blocks in both news encoder and decoder. ($\mathbf{a}$) is history encoder, ($\mathbf{b}$) is personalized news encoder, and ($\mathbf{c}$) is user-guided decoder.