paper-with-me

홈 › Papers

PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer

2023-11-14 · Huashan Sun, Yixiao Wu, Yuhao Ye, Yizhe Yang, Yinghao Li, Jiawei Li, Yang Gao

Language style is necessary for AI systems to understand and generate diverse human language accurately. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information.

📄 PDF Abstract BibTeX arXiv:2311.08389

Code (2)

shs910/psst 공식 구현
shs910/tsst 공식 구현

Tasks

SentenceStyle TransferText Style Transfer

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

PSSTRNet: Progressive Segmentation-guided Scene Text Removal Network

2023-06-13 · Guangtao Lyu, Anna Zhu

Scene text removal (STR) is a challenging task due to the complex text fonts, colors, sizes, and background textures in scene images. However, most previous methods learn both text location and background inpainting impl…

DecoderSegmentationText Segmentation

Pareto Self-Supervised Training for Few-Shot Learning

2021-04-16 · CVPR 2021 1 · Zhengyu Chen, Jixie Ge, Heshen Zhan, Siteng Huang 외

While few-shot learning (FSL) aims for rapid generalization to new concepts with little supervision, self-supervised learning (SSL) constructs supervisory signals directly computed from unlabeled data. Exploiting the com…

Auxiliary LearningFew-Shot LearningInductive BiasSelf-Supervised Learning

Joint Optimization for Cooperative Image Captioning

2019-10-01 · ICCV 2019 10 · Gilad Vered, Gal Oren, Yuval Atzmon, Gal Chechik

When describing images with natural language, descriptions can be made more informative if tuned for downstream tasks. This can be achieved by training two networks: a "speaker" that generates sentences given an image an…

Image Captioning

Cooperative image captioning

2019-07-26 · Gilad Vered, Gal Oren, Yuval Atzmon, Gal Chechik

When describing images with natural language, the descriptions can be made more informative if tuned using downstream tasks. This is often achieved by training two networks: a "speaker network" that generates sentences g…

Image Captioning

The Post-Stroke Speech Transcription (PSST) Challenge

2022-06-01 · RaPID (LREC) 2022 6 · Robert C. Gale, Mikala Fleegle, Gerasimos Fergadiotis, Steven Bedrick

We present the outcome of the Post-Stroke Speech Transcription (PSST) challenge. For the challenge, we prepared a new data resource of responses to two confrontation naming tests found in AphasiaBank, extracting audio an…