Related papers: Style Transfer for Texts: Retrain, Report Errors, …

Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts. Concept learning models, however, have been shown to…

The widely-used automatic evaluation metrics cannot adequately reflect the fluency of the translations. The n-gram-based metrics, like BLEU, limit the maximum length of matched fragments to n and cannot catch the matched fragments longer…

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…

Style-transfer is a process of migrating a style from a given image to the content of another, synthesizing a new image which is an artistic mixture of the two. Recent work on this problem adopting Convolutional Neural-networks (CNN)…

Arbitrary style transfer is an important problem in computer vision that aims to transfer style patterns from an arbitrary style image to a given content image. However, current methods either rely on slow iterative optimization or fast…

Source code summaries are important for program comprehension and maintenance. However, there are plenty of programs with missing, outdated, or mismatched summaries. Recently, deep learning techniques have been exploited to automatically…

Text style transfer without parallel data has achieved some practical success. However, in the scenario where less data is available, these methods may yield poor performance. In this paper, we examine domain adaptation for text style…

In this work we investigate different avenues of improving the Neural Algorithm of Artistic Style (by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge, arXiv:1508.06576). While showing great results when transferring homogeneous and…

Parameter transfer is a central paradigm in transfer learning, enabling knowledge reuse across tasks and domains by sharing model parameters between upstream and downstream models. However, when only a subset of parameters from the upstream…

Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics (such as BERTScore or MoverScore) are based on black-box language models such as BERT or XLM-R. They often achieve strong correlations with human…

Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model when transferred from a source task to a given target task.…

There has been fascinating work on creating artistic transformations of images by Gatys. This was revolutionary in how we can in some sense alter the 'style' of an image while generally preserving its 'content'. In our work, we present a…

Textual deception constitutes a major problem for online security. Many studies have argued that deceptiveness leaves traces in writing style, which could be detected using text classification techniques. By conducting an extensive…

Reranking methods in machine translation aim to close the gap between common evaluation metrics (e.g. BLEU) and maximum likelihood learning and decoding algorithms. Prior works address this challenge by training models to rerank beam search…

In natural language processing tasks performance of the models is often measured with some non-differentiable metric, such as BLEU score. To use efficient gradient-based methods for optimization, it is a common workaround to optimize some…

Universal style transfer aims to transfer arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or…

Transfer learning is a useful technique for achieving improved performance and reducing training costs by leveraging the knowledge gained from source tasks and applying it to target tasks. Assessing the effectiveness of transfer learning…

Commit messages are natural language descriptions of code changes, which are important for program understanding and maintenance. However, writing commit messages manually is time-consuming and laborious, especially when the code is updated…

We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs. Reference strings are scored for quality by human raters on a scale of [-1, +1]…

In this paper, we discuss different methods which use meta information and richer context that may accompany source language input to improve machine translation quality. We focus on category information of input text as meta information,…