paper-with-me

Papers

P-Masking: Power Law Masking Improves Multi-attribute Controlled Generation

2024-10-31 · Mohamed Elgaar, Hadi Amiri

We introduce LingGen, a novel approach for controlled text generation that offers precise control over a wide array of linguistic attributes, even as the number of attributes varies. LingGen employs a dynamic P-MASKING strategy, which samples masking rates from a power law distribution during training. This innovative approach enables the model to develop robust representations and adapt its attribute control capabilities across a variable number of attributes, from a single attribute to multiple complex configurations. The P-MASKING technique enhances LingGen's ability to manage different levels of attribute visibility, resulting in superior performance in multi-attribute generation tasks. Our experiments demonstrate that LingGen surpasses current state-of-the-art models in both attribute control accuracy and text fluency, particularly excelling in scenarios with varying attribute demands. Additionally, our ablation studies highlight the effectiveness of P-MASKING and the influence of different base language models on performance. These findings demonstrate LingGen's potential for applications requiring precise and adaptable control over multiple linguistic attributes in text generation.

📄 PDF Abstract BibTeX arXiv:2410.24201

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeText Generation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Extreme Multi-Label Classification with Label Masking for Product Attribute Value Extraction

2022-05-01 · ECNLP (ACL) 2022 5 · Wei-Te Chen, Yandi Xia, Keiji Shinzato

Although most studies have treated attribute value extraction (AVE) as named entity recognition, these approaches are not practical in real-world e-commerce platforms because they perform poorly, and require canonicaliza…

AttributeAttribute Value ExtractionExtreme Multi-Label ClassificationMulti-Label Classification+4

Token Masking Improves Transformer-Based Text Classification

2025-05-16 · Xianglong Xu, John Bowen, Rojin Taheri

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet the…

AttributeClassificationLanguage IdentificationSentiment Analysis+2

PMI-Masking: Principled masking of correlated spans

2020-10-05 · ICLR 2021 1 · Yoav Levine, Barak Lenz, Opher Lieber, Omri Abend 외

Masking tokens uniformly at random constitutes a common flaw in the pretraining of Masked Language Models (MLMs) such as BERT. We show that such uniform masking allows an MLM to minimize its training objective by latchin…

Structured-Noise Masked Modeling for Video, Audio and Beyond

2025-03-20 · Aritra Bhowmik, Fida Mohammad Thoker, Carlos Hinojosa, Bernard Ghanem 외

Masked modeling has emerged as a powerful self-supervised learning framework, but existing methods largely rely on random masking, disregarding the structural properties of different modalities. In this work, we introduc…

Representation LearningSelf-Supervised Learning

Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions

2024-02-21 · Lei Pan, Yunshi Lan, Yang Li, Weining Qian

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its…

In-Context LearningKnowledge DistillationSentenceStyle Transfer+2