Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSyntax Matters! Syntax-Controlled in Text Style Transfer
بناء جملة!بناء الجملة تسيطر عليها في نقل نمط النص
431
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعتمد أساليب نقل نمط النص الحالي (TST) على أسلوب الطبقات لتفكيك سمات محتوى النص والأناقة لنقل نمط النص. في حين أن المصنف الأسلوب يلعب دورا حاسما في طرق TST الحالية، لا يوجد تحقيق معروف على تأثيره على أساليب TST. في هذه الورقة، نقوم بإجراء دراسة تجريبية عن قيود أقراص الطبقات المستخدمة في طرق TST الحالية. لقد أظهرنا أن مصنفات النمط الموجودة لا يمكنهم تعلم بناء جملة الجملة بشكل فعال وفي نهاية المطاف أداء نماذج TST الحالية. لمعالجة هذه المشكلة، نقترح نموذجا جديدا للجيل القابل للتحكم في بناء الجملة، والذي يتضمن مصنف بنمط بناء بناء الجملة يضمن التمثيلات الكامنة المستفادة التي تم التعهد بها بفعالية برياحة هيكل الجملة ل TST. من خلال تجارب واسعة على مهام نقل نمط نصية شعبية، نوضح أن طريقةنا المقترحة تتفوق بشكل كبير على اثني عشر طريقا حديثة. أظهرت دراسات الحالة لدينا أيضا قدرة SACG على توليد جمل ذات أسلوب يستهدف بطلاقة حافظت على المحتوى الأصلي.
Existing text style transfer (TST) methods rely on style classifiers to disentangle the text's content and style attributes for text style transfer. While the style classifier plays a critical role in existing TST methods, there is no known investigation on its effect on the TST methods. In this paper, we conduct an empirical study on the limitations of the style classifiers used in existing TST methods. We demonstrated that the existing style classifiers cannot learn sentence syntax effectively and ultimately worsen existing TST models' performance. To address this issue, we propose a novel Syntax-Aware Controllable Generation (SACG) model, which includes a syntax-aware style classifier that ensures learned style latent representations effectively capture the sentence structure for TST. Through extensive experiments on two popular text style transfer tasks, we show that our proposed method significantly outperforms twelve state-of-the-art methods. Our case studies have also demonstrated SACG's ability to generate fluent target-style sentences that preserved the original content.
References used
https://aclanthology.org/
rate research
Read More
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.
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.
Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make t
hem appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more accurate in inducing syntactic structures than competing unsupervised systems. On the English WSJ corpus, our models achieve an unlabeled F1 score of 68.9 for constituency parsing.
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.
This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks
that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results. In this tutorial, we will first introduce the background and the latest progress of syntactic parsing and SRL/NMT. Then, we will summarize the key evidence about the syntactic impacts over these two concerning tasks, and explore the behind reasons from both computational and linguistic backgrounds.
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
