Controlling Linguistic Style Aspects in Neural Language Generation

Ficler, Jessica; Goldberg, Yoav

doi:10.48550/arxiv.1707.02633

Cited by 34 publications

(41 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various works have studied guided generation for images [54] and language [55,56]. Several works [57,58,59,60,61,62] have explored training or fine-tuning of models for controllable text generation. Class-conditional language models can also be used to learn disciminators to guide generation [63,55,64,65].…”

Section: Conditional Language Generationmentioning

confidence: 99%

Decision Transformer: Reinforcement Learning via Sequence Modeling

Chen¹,

Rajeswaran²,

Lee³

et al. 2021

Preprint

View full text Add to dashboard Cite

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x and BERT. In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Unlike prior approaches to RL that fit value functions or compute policy gradients, Decision Transformer simply outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired return (reward), past states, and actions, our Decision Transformer model can generate future actions that achieve the desired return. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.

show abstract

Section: Conditional Language Generationmentioning

confidence: 99%

Decision Transformer: Reinforcement Learning via Sequence Modeling

Chen¹,

Rajeswaran²,

Lee³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, the development of deep learning (DL) has given rise to a series of studies on DLdriven controllable text generation (CTG), which has brought genuine breakthroughs in this field. Early approaches are based on sequential models and style embedding [Ficler and Goldberg 2017;Li et al 2016b], and achieved some promising progress. After that, there is a surge of methods based on deep generative models, such as Variational Autoencoders (VAEs) [Hu et al 2017a;Sohn et al 2015;Vechtomova et al 2018;, Generative Adversarial 111:3 Nets (GANs) [Scialom et al 2020;Wang and Wan 2018], and Energy-based Models [Bhattacharyya et al 2021;Deng et al 2020;Tu et al 2020;Zhao et al 2017].…”

Section: Ai Chatbot Story Generationmentioning

confidence: 99%

A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models

Zhang¹,

Song²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Controllable Text Generation (CTG) is emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that are more natural and better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the lower level of interpretability of deep neural networks, the controllability of these methods need to be guaranteed. To this end, controllable text generation using transformer-based PLMs has become a rapidly growing yet challenging new research hotspot. A diverse range of approaches have emerged in the recent 3-4 years, targeting different CTG tasks which may require different types of controlled constraints. In this paper, we present a systematic critical review on the common tasks, main approaches and evaluation methods in this area. Finally, we discuss the challenges that the field is facing, and put forward various promising future directions. To the best of our knowledge, this is the first survey paper to summarize CTG techniques from the perspective of PLMs. We hope it can help researchers in related fields to quickly track the academic frontier, providing them with a landscape of the area and a roadmap for future research.

show abstract

“…One line of work fine-tunes a pretrained model for a desired attribute (Ficler and Goldberg, 2017;Yu et al, 2017;Ziegler et al, 2019). The result is a class-conditional language model (CCLM).…”

Section: Related Workmentioning

confidence: 99%

FUDGE: Controlled Text Generation With Future Discriminators

Yang,

Klein

2021

Preprint

View full text Add to dashboard Cite

We propose Future Discriminators for Generation (FUDGE), a flexible and modular method for controlled text generation. Given a preexisting model G for generating text from a distribution of interest, FUDGE enables conditioning on a desired attribute a (for example, formality) while requiring access only to G's output logits. FUDGE learns an attribute predictor operating on a partial sequence, and uses this predictor's outputs to adjust G's original probabilities. We show that FUDGE models terms corresponding to a Bayesian decomposition of the conditional distribution of G given attribute a. Moreover, FUDGE can easily compose predictors for multiple desired attributes. We evaluate FUDGE on three tasks -couplet completion in poetry, topic control in language generation, and formality change in machine translation -and observe gains in all three tasks.

show abstract

Controlling Linguistic Style Aspects in Neural Language Generation

Cited by 34 publications

References 0 publications

Decision Transformer: Reinforcement Learning via Sequence Modeling

Decision Transformer: Reinforcement Learning via Sequence Modeling

A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models

FUDGE: Controlled Text Generation With Future Discriminators

Contact Info

Product

Resources

About