# Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation

arXiv: https://arxiv.org/abs/2004.03875 · HTML: https://mlsanity.com/paper/2004.03875/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://mlsanity.com/paper/2402.17633/) (2024)
- [SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation](https://mlsanity.com/paper/2403.17768/) (2024)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [Contrastive Learning enhanced Author-Style Headline Generation](https://mlsanity.com/paper/2211.03305/) (2022)
- [CUSTOM: Aspect-Oriented Product Summarization for E-Commerce](https://mlsanity.com/paper/2108.08010/) (2021)
- [BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion](https://mlsanity.com/paper/2501.01069/) (2025)
- [Abstractive Opinion Tagging](https://mlsanity.com/paper/2101.06880/) (2021)
- [Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System](https://mlsanity.com/paper/2104.11454/) (2021)

## Abstract (arXiv)

News headline generation aims to produce a short sentence to attract readers to read the news. One news article often contains multiple keyphrases that are of interest to different users, which can naturally have multiple reasonable headlines. However, most existing methods focus on the single headline generation. In this paper, we propose generating multiple headlines with keyphrases of user interests, whose main idea is to generate multiple keyphrases of interest to users for the news first, and then generate multiple keyphrase-relevant headlines. We propose a multi-source Transformer decoder, which takes three sources as inputs: (a) keyphrase, (b) keyphrase-filtered article, and (c) original article to generate keyphrase-relevant, high-quality, and diverse headlines. Furthermore, we propose a simple and effective method to mine the keyphrases of interest in the news article and build a first large-scale keyphrase-aware news headline corpus, which contains over 180K aligned triples of <news article, headline, keyphrase>. Extensive experimental comparisons on the real-world dataset show that the proposed method achieves state-of-the-art results in terms of quality and diversity