Controlling Styles in Neural Machine Translation with Activation Prompt

• URL: http://arxiv.org/abs/2212.08909v2
• Date: Mon, 29 May 2023 02:59:07 GMT
• Title: Controlling Styles in Neural Machine Translation with Activation Prompt
• Authors: Yifan Wang, Zewei Sun, Shanbo Cheng, Weiguo Zheng, Mingxuan Wang
• Abstract summary: Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is crucial for enhancing user experience. This paper presents a new benchmark and approach for controlling styles in NMT. We propose a method named style activation prompt (StyleAP) by prompts from stylized monolingual corpus, which does not require extra fine-tuning.
• Score: 34.53183905545485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is crucial for enhancing user experience. Earlier studies on this topic typically concentrate on regulating the level of formality and achieve some progress in this area. However, they still encounter two major challenges. The first is the difficulty in style evaluation. The style comprises various aspects such as lexis, syntax, and others that provide abundant information. Nevertheless, only formality has been thoroughly investigated. The second challenge involves excessive dependence on incremental adjustments, particularly when new styles are necessary. To address both challenges, this paper presents a new benchmark and approach. A multiway stylized machine translation (MSMT) benchmark is introduced, incorporating diverse categories of styles across four linguistic domains. Then, we propose a method named style activation prompt (StyleAP) by retrieving prompts from stylized monolingual corpus, which does not require extra fine-tuning. Experiments show that StyleAP could effectively control the style of translation and achieve remarkable performance.

Related papers

• SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning [22.04285529067442]
  Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning is proposed. SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. Experiments show SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-22T11:34:48Z)
• Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation [15.959784404955402]
  Textual style expresses a diverse set of information, including interpersonal dynamics (e.g., formality) and the author's emotions or attitudes (e.g., disgust) An open question is how language models can be explicitly controlled so that they weave together target styles when generating text. One approach to such controlled generation is multi-objective reinforcement learning (RL) We investigate various formulations of multi-style rewards, including calibrated outputs from discriminators and dynamic weighting by discriminator magnitudes.
  arXiv  Detail & Related papers  (2024-02-21T22:02:37Z)
• Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations [12.891344121936902]
  Expressive text-to-speech (TTS) aims to synthesize speeches with human-like tones, moods, or even artistic attributes. Recent advancements in TTS empower users with the ability to directly control synthesis style through natural language prompts. We present FreeStyleTTS (FS-TTS), a controllable expressive TTS model with minimal human annotations.
  arXiv  Detail & Related papers  (2023-11-02T14:20:37Z)
• MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer [82.37710853235535]
  Unsupervised text style transfer task aims to rewrite a text into target style while preserving its main content. Traditional methods rely on the use of a fixed-sized vector to regulate text style, which is difficult to accurately convey the style strength for each individual token. Our proposed method addresses this issue by assigning individual style vector to each token in a text, allowing for fine-grained control and manipulation of the style strength.
  arXiv  Detail & Related papers  (2023-06-12T13:12:29Z)
• Conversation Style Transfer using Few-Shot Learning [56.43383396058639]
  In this paper, we introduce conversation style transfer as a few-shot learning problem. We propose a novel in-context learning approach to solve the task with style-free dialogues as a pivot. We show that conversation style transfer can also benefit downstream tasks.
  arXiv  Detail & Related papers  (2023-02-16T15:27:00Z)
• ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting [121.11880210592497]
  We argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. We propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting.
  arXiv  Detail & Related papers  (2022-11-19T03:50:33Z)
• Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework [4.827674529956945]
  We propose the modular, fine-grained and content-controlled similarity-based STyle EvaLuation framework (STEL) to test the performance of any model that can compare two sentences on style. We illustrate STEL with two general dimensions of style (formal/informal and simple/complex) as well as two specific characteristics of style (contrac'tion and numb3r substitution) BERT-based methods outperform simple versions of commonly used style measures like 3-grams, punctuation frequency and LIWC-based approaches.
  arXiv  Detail & Related papers  (2021-09-10T12:03:19Z)
• StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer [90.6768813620898]
  Style transfer aims to controllably generate text with targeted stylistic changes while maintaining core meaning from the source sentence constant. We introduce a large-scale benchmark, StylePTB, with paired sentences undergoing 21 fine-grained stylistic changes spanning atomic lexical, syntactic, semantic, and thematic transfers of text. We find that existing methods on StylePTB struggle to model fine-grained changes and have an even more difficult time composing multiple styles.
  arXiv  Detail & Related papers  (2021-04-12T04:25:09Z)
• Improving Disentangled Text Representation Learning with Information-Theoretic Guidance [99.68851329919858]
  discrete nature of natural language makes disentangling of textual representations more challenging. Inspired by information theory, we propose a novel method that effectively manifests disentangled representations of text. Experiments on both conditional text generation and text-style transfer demonstrate the high quality of our disentangled representation.
  arXiv  Detail & Related papers  (2020-06-01T03:36:01Z)

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.