Controllable Natural Language Generation with Contrastive Prefixes

• URL: http://arxiv.org/abs/2202.13257v1
• Date: Sun, 27 Feb 2022 00:31:03 GMT
• Title: Controllable Natural Language Generation with Contrastive Prefixes
• Authors: Jing Qian, Li Dong, Yelong Shen, Furu Wei, Weizhu Chen
• Abstract summary: GPT2 generation utilizes a set of small attribute-specific vectors, called prefixes, to steer natural language generation. We propose a novel supervised method and also an unsupervised method to train the prefixes for single-aspect control. Experimental results on both single-aspect and multi-aspect control show that our methods can guide generation towards the desired attributes while keeping high linguistic quality.
• Score: 120.12778570283956
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: To guide the generation of large pretrained language models (LM), previous work has focused on directly fine-tuning the language model or utilizing an attribute discriminator. In this work, we propose a novel lightweight framework for controllable GPT2 generation, which utilizes a set of small attribute-specific vectors, called prefixes, to steer natural language generation. Different from prefix-tuning, where each prefix is trained independently, we take the relationship among prefixes into consideration and train multiple prefixes simultaneously. We propose a novel supervised method and also an unsupervised method to train the prefixes for single-aspect control while the combination of these two methods can achieve multi-aspect control. Experimental results on both single-aspect and multi-aspect control show that our methods can guide generation towards the desired attributes while keeping high linguistic quality.

Related papers

• CalliffusionV2: Personalized Natural Calligraphy Generation with Flexible Multi-modal Control [8.2481475383203]
  CalliffusionV2 is a novel system designed to produce natural Chinese calligraphy with flexible multi-modal control. It excels at creating a broad range of characters and can quickly learn new styles through a few-shot learning approach. It is also capable of generating non-Chinese characters without prior training.
  arXiv  Detail & Related papers  (2024-10-03T20:26:54Z)
• DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation [57.07295906718989]
  Constrained decoding approaches aim to control the meaning or style of text generated by a Pre-trained Language Model (PLM) using specific target words during inference. We propose a novel decoding framework, DECIDER, which enables us to program rules on how we complete tasks to control a PLM.
  arXiv  Detail & Related papers  (2024-03-04T11:49:08Z)
• Controlled Text Generation with Natural Language Instructions [74.88938055638636]
  InstructCTG is a controlled text generation framework that incorporates different constraints. We first extract the underlying constraints of natural texts through a combination of off-the-shelf NLP tools and simple verbalizes. By prepending natural language descriptions of the constraints and a few demonstrations, we fine-tune a pre-trained language model to incorporate various types of constraints.
  arXiv  Detail & Related papers  (2023-04-27T15:56:34Z)
• An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation [70.77243918587321]
  Multi-aspect controllable text generation that controls generated text in multiple aspects has attracted increasing attention. We provide a theoretical lower bound for the interference and empirically found that the interference grows with the number of layers where prefixes are inserted. We propose using trainable gates to normalize the intervention of prefixes to restrain the growing interference.
  arXiv  Detail & Related papers  (2022-12-19T11:53:59Z)
• Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models [58.990214815032495]
  Large-scale pre-trained language models have achieved great success on natural language generation tasks. BCLMs have been shown to be efficient in controllable language generation. We propose a "Gemini Discriminator" for controllable language generation which alleviates the mismatch problem with a small computational cost.
  arXiv  Detail & Related papers  (2022-06-11T12:52:32Z)
• A Plug-and-Play Method for Controlled Text Generation [38.283313068622085]
  We present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sentence. Despite the simplicity of this approach, we see it works incredibly well in practice.
  arXiv  Detail & Related papers  (2021-09-20T17:27:03Z)
• Attribute Alignment: Controlling Text Generation from Pre-trained Language Models [46.19190007510232]
  We propose a simple and flexible method for controlling text generation by aligning disentangled attribute representations. In contrast to recent efforts on training a discriminator to perturb the token level distribution for an attribute, we use the same data to learn an alignment function to guide the pre-trained, non-controlled language model to generate texts with the target attribute without changing the original language model parameters.
  arXiv  Detail & Related papers  (2021-03-20T01:51:32Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.