Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn Learning Text Style Transfer with Direct Rewards
على تعلم نقل نمط النص مع المكافآت المباشرة
389
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في معظم الحالات، فإن الافتقار إلى Corpora الموازي يجعل من المستحيل مباشرة على تدريب النماذج الخاضعة للإشراف لمهمة نقل نمط النص.في هذه الورقة، نستكشف خوارزميات التدريب التي تقوم بدلا من ذلك تحسين وظائف المكافآت التي تنظر صراحة في جوانب مختلفة من النواتج التي يتم تحويلها بالسليب.على وجه الخصوص، نحن نستفيد مقاييس التشابه الدلالي المستخدمة في الأصل لنماذج الترجمة الآلية العصبية بشكل جيد لتقييم الحفاظ على المحتوى بشكل صريح بين مخرجات النظام ونصوص الإدخال.نحقق أيضا في نقاط الضعف المحتملة للمقاييس التلقائية الحالية واقتراح استراتيجيات فعالة لاستخدام هذه المقاييس للتدريب.تظهر النتائج التجريبية أن طرازنا يوفر مكاسب كبيرة في كل من التقييم التلقائي والإنساني على أساس الأساس القوي، مما يشير إلى فعالية أساليبنا المقترحة واستراتيجيات التدريب.
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 different 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.
References used
https://aclanthology.org/
rate research
Read More
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.
The style transfer task (here style is used in a broad authorial'' sense with many aspects including register, sentence structure, and vocabulary choice) takes text input and rewrites it in a specified target style preserving the meaning, but alterin
g the style of the source text to match that of the target. Much of the existing research on this task depends on the use of parallel datasets. In this work we employ recent results in unsupervised cross-lingual language modeling (XLM) and machine translation to effect style transfer while treating the input data as unaligned. First, we show that adding content embeddings'' to the XLM which capture human-specified groupings of subject matter can improve performance over the baseline model. Evaluation of style transfer has often relied on metrics designed for machine translation which have received criticism of their suitability for this task. As a second contribution, we propose the use of a suite of classical stylometrics as a useful complement for evaluation. We select a few such measures and include these in the analysis of our results.
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.
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 investiga
tion 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.
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
