Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization

• URL: http://arxiv.org/abs/2010.05090v1
• Date: Sat, 10 Oct 2020 21:05:56 GMT
• Title: Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization
• Authors: Kunal Chawla, Diyi Yang
• Abstract summary: Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences. We propose a semi-supervised formality style transfer model that utilizes a language model-based discriminator to maximize the likelihood of the output sentence being formal. Experiments showed that our model outperformed previous state-of-the-art baselines significantly in terms of both automated metrics and human judgement.
• Score: 52.867459839641526
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supervised formality style transfer model that utilizes a language model-based discriminator to maximize the likelihood of the output sentence being formal, which allows us to use maximization of token-level conditional probabilities for training. We further propose to maximize mutual information between source and target styles as our training objective instead of maximizing the regular likelihood that often leads to repetitive and trivial generated responses. Experiments showed that our model outperformed previous state-of-the-art baselines significantly in terms of both automated metrics and human judgement. We further generalized our model to unsupervised text style transfer task, and achieved significant improvements on two benchmark sentiment style transfer datasets.

Related papers

• Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking [17.475727043819635]
  Transferability Estimation (TE) has emerged as an effective approach to model selection. We propose to compute the expected rank as transferability, explicitly reflecting the model's ranking capability. Our resulting method, Adaptive Ranking Transferability (AiRTran), can effectively capture subtle differences between models.
  arXiv  Detail & Related papers  (2024-09-24T15:48:03Z)
• Aligning Large Language Models with Counterfactual DPO [1.8130068086063336]
  This paper explores the utilization of counterfactual prompting to align the model's style without relying on human intervention. We demonstrate that this method effectively instils desirable behaviour, mitigates undesirable ones, and encourages the model to disregard inappropriate instructions.
  arXiv  Detail & Related papers  (2024-01-17T19:43:43Z)
• Fine-grained Text Style Transfer with Diffusion-Based Language Models [50.02698074338317]
  We trained a diffusion-based model on StylePTB dataset, the standard benchmark for fine-grained text style transfers. Our model was able to achieve state-of-the-art performance on both individual and compositional transfers.
  arXiv  Detail & Related papers  (2023-05-31T02:51:26Z)
• POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models [62.23255433487586]
  We propose an unsupervised fine-tuning framework to fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and target data.
  arXiv  Detail & Related papers  (2023-04-29T22:05:22Z)
• Non-Parallel Text Style Transfer with Self-Parallel Supervision [19.441780035577352]
  We propose LaMer, a novel text style transfer framework based on large-scale language models. LaMer first mines the roughly parallel expressions in the non-parallel datasets with scene graphs, and then employs MLE training, followed by imitation learning refinement, to leverage the intrinsic parallelism within the data. On two benchmark tasks (sentiment & formality transfer) and a newly proposed challenging task (political stance transfer), our model achieves qualitative advances in transfer accuracy, content preservation, and fluency.
  arXiv  Detail & Related papers  (2022-04-18T01:38:35Z)
• GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer [119.70961704127157]
  Non-parallel text style transfer has attracted increasing research interests in recent years. Current approaches still lack the ability to preserve the content and even logic of original sentences. We propose a method called Graph Transformer based Auto-GTAE, which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level.
  arXiv  Detail & Related papers  (2021-02-01T11:08:45Z)
• 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)
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models [39.526613595499356]
  We introduce a KL loss and a style classifier to steer response generation towards the target style in both a word-level and a sentence-level. Our model can significantly outperform state-of-the-art methods in terms of both style consistency and contextual coherence.
  arXiv  Detail & Related papers  (2020-10-06T09:29:50Z)
• A Probabilistic Formulation of Unsupervised Text Style Transfer [128.80213211598752]
  We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. By hypothesizing a parallel latent sequence that generates each observed sequence, our model learns to transform sequences from one domain to another in a completely unsupervised fashion.
  arXiv  Detail & Related papers  (2020-02-10T16:20:49Z)

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.