Papers with headline generation tasks

5 papers
Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning (2022.aacl-main)

Copied to clipboard

Challenge: Recent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive and would be small-scale.
Approach: They propose a novel duality fine-tuning method to capture more information from limited data and build connections between tasks.
Outcome: The proposed method can capture more information from limited data, build connections between separate tasks, and is suitable for less-data constrained generation tasks.
Select and Attend: Towards Controllable Content Selection in Text Generation (D19-1)

Copied to clipboard

Challenge: Recent neural network models conflate content selection and surface realization into a black-box architecture, resulting in content to be described in text cannot be explicitly controlled.
Approach: They propose to decouple content selection from the decoder to allow finer-grained control over the generation.
Outcome: The proposed model can be trained end-to-end without human annotations and achieves promising results in data-totext and headline generation tasks.
Extractive Headline Generation Based on Learning to Rank for Community Question Answering (C18-1)

Copied to clipboard

Challenge: Community question answering (CQA) forums do not always have appropriate headlines because of user-generated content.
Approach: They propose an extractive headline generation method that extracts the most informative substring from each question as its headline.
Outcome: The proposed method outperforms baselines including a prefix-based method . it uses the prefix of a question as its headline to create the most informative substring .
MediaHG: Rethinking Eye-catchy Features in Social Media Headline Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Creating a good headline on social media platforms requires a disentanglement-based model to balance the content and contextual features.
Approach: They propose a disentanglement-based headline generation model which can balance the content and contextual features by incorporating contrastive learning and auxiliary multi-tasking to choose the best domain-suitable headline.
Outcome: The proposed model can balance content and contextual features, while allowing bloggers to obtain more site traffic and profits while readers can have easier access to topics of interest.
CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China (2025.emnlp-main)

Copied to clipboard

Challenge: Minority languages in China face significant challenges due to their unique writing systems, which differ from international standards.
Approach: They propose a dataset specifically curated for headline generation tasks for minority languages in China . they propose 50,000 entries each for Uyghur and Mongolian, and a test set annotated by native speakers .
Outcome: The proposed dataset will help improve headline generation in minority languages . it includes 100,000 entries for Tibetan, 50,000 entries each for Uyghur and Mongolian .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations