Lune

EMNLP Findings2021

Controlled Neural Sentence-Level Reframing of News Articles

Wei-Fan Chen, Khalid Al Khatib, Benno Stein, Henning Wachsmuth

Abstract

Framing a news article means to portray the reported event from a specific perspective, e.g., from an economic or a health perspective. Reframing means to change this perspective. Depending on the audience or the submessage, reframing can become necessary to achieve the desired effect on the readers. Reframing is related to adapting style and sentiment, which can be tackled with neural text generation techniques. However, it is more challenging since changing a frame requires rewriting entire sentences rather than single phrases. In this paper, we study how to computationally reframe sentences in news articles while maintaining their coherence to the context. We treat reframing as a sentence-level fill-in-the-blank task for which we train neural models on an existing media frame corpus. To guide the training, we propose three strategies: framed-language pretraining, named-entity preservation, and adversarial learning. We evaluate respective models automatically and manually for topic consistency, coherence, and successful reframing. Our results indicate that generating properlyframed text works well but with tradeoffs.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Plug and Play Autoencoders for Conditional Text Generation cites Educating Text Autoencoders: Latent Representation Guidance via Denoising
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Training Models to Generate, Recognize, and Reframe Unhelpful ThoughtsMounica Maddela, Megan Ung, Jing Xu, Andrea Madotto et al.ACL 2023 · 2 citations
  2. Identifying the Human Values behind ArgumentsJohannes Kiesel, Milad Alshomary, Nicolas Handke, Xiaoni Cai et al.ACL 2022

Builds on3

  1. Educating Text Autoencoders: Latent Representation Guidance via DenoisingTianxiao Shen, Jonas Mueller, Regina Barzilay, Tommi S. JaakkolaICML 2020 · 74 citations
  2. Detecting Media Bias in News Articles using Gaussian Bias DistributionsWei-Fan Chen, Khalid Al Khatib, Benno Stein, Henning WachsmuthEMNLP Findings 2020 · 30 citations
  3. Plug and Play Autoencoders for Conditional Text GenerationFlorian Mai, Nikolaos Pappas, Ivan Montero, Noah A. Smith et al.EMNLP 2020 · 24 citations

Related papers

  1. ReelFramer: Human-AI Co-Creation for News-to-Video TranslationSitong Wang, Samia Menon, Tao Long, Keren Henderson et al.CHI 2024 · 47 citations
  2. Inducing Positive Perspectives with Text ReframingCaleb Ziems, Minzhi Li, Anthony Zhang, Diyi YangACL 2022 · 46 citations
  3. Using Social and Linguistic Information to Adapt Pretrained Representations for Political Perspective IdentificationChang Li, Dan GoldwasserACL Findings 2021 · 24 citations
  4. Seeing the Same Story Differently: Framing-Divergent Event Coreference for Computational Framing AnalysisJin Zhao, Xinrui Hu, Nianwen XueEMNLP 2025
  5. Sentiment-Aware Word and Sentence Level Pre-training for Sentiment AnalysisShuai Fan, Chen Lin, Haonan Li, Zhenghao Lin et al.EMNLP 2022 · 20 citations
Dusk over the sea between two cliffs drawn in fine vertical lines