Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userStylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
StyleptB: معيار تركيبي لنقل نمط النص الذي يحتفل بخير
202
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف نقل نمط النص إلى توليد نص محكم مع التغييرات الأسلوبية المستهدفة مع الحفاظ على المعنى الأساسي من ثابت الجملة. تركز العديد من معايير نقل النمط الموجودة في المقام الأول على التغييرات الدلالية الفردية الفردية (E.G. إيجابية إلى سلبية)، والتي تمكن من إمكانية التحكم في مستوى عال ولكنها لا تقدم تحكما بخير ينطوي على هيكل جملة، والتركيز ومضمون الجملة. في هذه الورقة، نقدم معيارا واسع النطاق، StyleptB، مع (1) جمل مقترنة تخضع 21 تغييرات أسلوبية حبيبة على غرامة تمتد عبر التحويلات المعجمية البسيطة والمعدة والدلية والمواورة، وكذلك (2) تركيبات متعددة التحويلات التي تسمح نمذجة التغييرات الأسلالية المحتلة الجميلة كقوانيات لتحويل أكثر تعقيدا رفيعة المستوى. بقياس الأساليب الحالية على StyleptB، نجد أنهم يكافحون من أجل تغييرات التغييرات الدقيقة والحصول على وقت أكثر صعوبة في تكوين أنماط متعددة. ونتيجة لذلك، فإن StyleptB يجلب تحديات جديدة نأمل أن يشجع البحث في المستقبل في نقل أسلوب نصي يمكن السيطرة عليها ونماذج تركيبية وتعلم تمثيلات DESENTANGLED. سيقدم حل هذه التحديات خطوات مهمة نحو جيل نص قابل للتحكم.
Text style transfer aims to controllably generate text with targeted stylistic changes while maintaining core meaning from the source sentence constant. Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e.g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence. In this paper, we introduce a large-scale benchmark, StylePTB, with (1) paired sentences undergoing 21 fine-grained stylistic changes spanning atomic lexical, syntactic, semantic, and thematic transfers of text, as well as (2) compositions of multiple transfers which allow modeling of fine-grained stylistic changes as building blocks for more complex, high-level transfers. By benchmarking existing methods on StylePTB, we find that they struggle to model fine-grained changes and have an even more difficult time composing multiple styles. As a result, StylePTB brings novel challenges that we hope will encourage future research in controllable text style transfer, compositional models, and learning disentangled representations. Solving these challenges would present important steps towards controllable text generation.
References used
https://aclanthology.org/
rate research
Read More
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian. Results on XFORMAL suggest that state-of-the-ar
t style transfer approaches perform close to simple baselines, indicating that style transfer is even more challenging when moving multilingual.
Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases. However, the
lacking of parallel corpus hinders the ability of these inductive learning methods on this task. As a result, it is likely to cause severe inconsistent style expressions, like the salad is rude'. To tackle this problem, we propose a novel transductive learning approach in this paper, based on a retrieval-based context-aware style representation. Specifically, an attentional encoder-decoder with a retriever framework is utilized. It involves top-K relevant sentences in the target style in the transfer process. In this way, we can learn a context-aware style embedding to alleviate the above inconsistency problem. In this paper, both sparse (BM25) and dense retrieval functions (MIPS) are used, and two objective functions are designed to facilitate joint learning. Experimental results show that our method outperforms several strong baselines. The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.
Learning a good latent representation is essential for text style transfer, which generates a new sentence by changing the attributes of a given sentence while preserving its content. Most previous works adopt disentangled latent representation learn
ing to realize style transfer. We propose a novel text style transfer algorithm with entangled latent representation, and introduce a style classifier that can regulate the latent structure and transfer style. Moreover, our algorithm for style transfer applies to both single-attribute and multi-attribute transfer. Extensive experimental results show that our method generally outperforms state-of-the-art approaches.
Text style transfer involves rewriting the content of a source sentence in a target style. Despite there being a number of style tasks with available data, there has been limited systematic discussion of how text style datasets relate to each other.
This understanding, however, is likely to have implications for selecting multiple data sources for model training. While it is prudent to consider inherent stylistic properties when determining these relationships, we also must consider how a style is realized in a particular dataset. In this paper, we conduct several empirical analyses of existing text style datasets. Based on our results, we propose a categorization of stylistic and dataset properties to consider when utilizing or comparing text style datasets.
In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. In this paper, we explore training algorithms that instead optimize reward functions that explicitly consider differ
ent aspects of the style-transferred outputs. In particular, we leverage semantic similarity metrics originally used for fine-tuning neural machine translation models to explicitly assess the preservation of content between system outputs and input texts. We also investigate the potential weaknesses of the existing automatic metrics and propose efficient strategies of using these metrics for training. The experimental results show that our model provides significant gains in both automatic and human evaluation over strong baselines, indicating the effectiveness of our proposed methods and training strategies.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
