Details
| Original language | English |
|---|---|
| Title of host publication | Findings of the Association for Computational Linguistics |
| Subtitle of host publication | EMNLP 2021 |
| Editors | Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-Tau Yih |
| Place of Publication | Punta Cana |
| Pages | 2683-2693 |
| Number of pages | 11 |
| Publication status | Published - Nov 2021 |
| Externally published | Yes |
| Event | 2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021 - Punta Cana, Dominican Republic Duration: 7 Nov 2021 → 11 Nov 2021 |
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.
ASJC Scopus subject areas
- Arts and Humanities(all)
- Language and Linguistics
- Social Sciences(all)
- Linguistics and Language
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Findings of the Association for Computational Linguistics: EMNLP 2021. ed. / Marie-Francine Moens; Xuanjing Huang; Lucia Specia; Scott Wen-Tau Yih. Punta Cana, 2021. p. 2683-2693.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research
}
TY - GEN
T1 - Controlled Neural Sentence-Level Reframing of News Articles
AU - Chen, Wei Fan
AU - Al-Khati, Khalid
AU - Stein, Benno
AU - Wachsmuth, Henning
N1 - Funding Information: This work was partially supported by the German Research Foundation (DFG) within the Collaborative Research Center "On-The-Fly Computing" (SFB 901/3) under the project number 160364472.
PY - 2021/11
Y1 - 2021/11
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85129203764&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.findings-emnlp.228
DO - 10.18653/v1/2021.findings-emnlp.228
M3 - Conference contribution
AN - SCOPUS:85129203764
SN - 9781955917100
SP - 2683
EP - 2693
BT - Findings of the Association for Computational Linguistics
A2 - Moens, Marie-Francine
A2 - Huang, Xuanjing
A2 - Specia, Lucia
A2 - Yih, Scott Wen-Tau
CY - Punta Cana
T2 - 2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
Y2 - 7 November 2021 through 11 November 2021
ER -