paper-with-me

Papers

Effective Unsupervised Constrained Text Generation based on Perturbed Masking

2024-04-24 · Findings (ACL) 2022 5 · Yingwen Fu, Wenjie Ou, Zhou Yu, Yue Lin

Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions and actions, which may cause unnecessary search steps. In this paper, we propose PMCTG to improve effectiveness by searching for the best edit position and action in each step. Specifically, PMCTG extends perturbed masking technique to effectively search for the most incongruent token to edit. Then it introduces four multi-aspect scoring functions to select edit action to further reduce search difficulty. Since PMCTG does not require supervised data, it could be applied to different generation tasks. We show that under the unsupervised setting, PMCTG achieves new state-of-the-art results in two representative tasks, namely keywords-to-sentence generation and paraphrasing.

📄 PDF Abstract BibTeX arXiv:2404.15877

Code (0)

등록된 구현이 없습니다.

Tasks

PositionSentenceText Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Effective Unsupervised Constrained Text Generation based on Perturbed Masking

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions which may cause unnecessa…

PositionSentenceText Generation

Gradient-guided Unsupervised Lexically Constrained Text Generation

2020-11-01 · EMNLP 2020 11 · Lei Sha

Lexically constrained generation requires the target sentence to satisfy some lexical constraints, such as containing some specific words or being the paraphrase to a given sentence, which is very important in many real-…

Paraphrase GenerationSentenceText Generation

PDSS: A Privacy-Preserving Framework for Step-by-Step Distillation of Large Language Models

2024-06-18 · Tao Fan, Yan Kang, Weijing Chen, Hanlin Gu 외

In the context of real-world applications, leveraging large language models (LLMs) for domain-specific tasks often faces two major challenges: domain-specific knowledge privacy and constrained resources. To address these…

DecoderLanguage ModelingLanguage ModellingMulti-Task Learning+3

Source-free Domain Adaptive Object Detection in Remote Sensing Images

2024-01-31 · Weixing Liu, Jun Liu, Xin Su, Han Nie 외

Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be ac…

Domain Adaptationobject-detectionObject DetectionSource Free Object Detection

Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching

2025-11-18 · Jintao Zhang, Mingyue Cheng, Zirui Liu, Xianquan Wang 외 arxiv

Time series generation is critical for a wide range of applications, which greatly supports downstream analytical and decision-making tasks. However, the inherent temporal heterogeneous induced by localized perturbations…