paper-with-me

홈 › Papers

Data-to-Text Generation with Style Imitation

2019-01-28 · Findings of the Association for Computational Linguistics 2020 · Shuai Lin, Wentao Wang, Zichao Yang, Xiaodan Liang, Frank F. Xu, Eric Xing, Zhiting Hu

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to determine the realization of text. Yet manual or automatic construction of high-quality templates is difficult, and a template acting as hard constraints could harm content fidelity when it does not match the record perfectly. We study a new way of stylistic control by using existing sentences as soft templates. That is, the model learns to imitate the writing style of any given exemplar sentence, with automatic adaptions to faithfully describe the content record. The problem is challenging due to the lack of parallel data. We develop a neural approach that includes a hybrid attention-copy mechanism, learns with weak supervisions, and is enhanced with a new content coverage constraint. We conduct experiments in restaurants and sports domains. Results show our approach achieves stronger performance than a range of comparison methods. Our approach balances well between content fidelity and style control given exemplars that match the records to varying degrees.

📄 PDF Abstract BibTeX arXiv:1901.09501

Code (1)

ha-lins/DTG-SI 공식 구현 tf

Tasks

Data-to-Text GenerationSentenceStyle TransferText Generation

Similar Papers 제목 키워드 기반

Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation

2024-09-14 · Chenxu Xiong, Ruibo Fu, Shuchen Shi, Zhengqi Wen 외

Current mainstream audio generation methods primarily rely on simple text prompts, often failing to capture the nuanced details necessary for multi-style audio generation. To address this limitation, the Sound Event Enha…

Audio GenerationStyle Transfer

Personalized Text Generation with Contrastive Activation Steering

2025-03-07 · Jinghao Zhang, YuTing Liu, Wenjie Wang, Qiang Liu 외

Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two…

parameter-efficient fine-tuningRAGRetrievalRetrieval-augmented Generation+1

Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion Model

2025-09-19 · Sidra Hanif, Longin Jan Latecki arxiv

Handwriting stroke generation is crucial for improving the performance of tasks such as handwriting recognition and writers order recovery. In handwriting stroke generation, it is significantly important to imitate the s…

Handwriting RecognitionImage Generation

AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer

2025-11-10 · Yulim So, Seokho Kang arxiv

Anomaly generation has been widely explored to address the scarcity of anomaly images in real-world data. However, existing methods typically suffer from at least one of the following limitations, hindering their practic…

Anomaly DetectionStyle Transfer

Zero-Shot Styled Text Image Generation, but Make It Autoregressive

2025-03-21 · CVPR 2025 1 · Vittorio Pippi, Fabio Quattrini, Silvia Cascianelli, Alessio Tonioni 외

Styled Handwritten Text Generation (HTG) has recently received attention from the computer vision and document analysis communities, which have developed several solutions, either GAN- or diffusion-based, that achieved p…

Image GenerationText Generation