DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting

Singh, Hrituraj; Verma, Gaurav; Srinivasan, Balaji Vasan

doi:10.18653/v1/2021.eacl-main.73

Cited by 5 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, we see more datasets that are generated by a machine [106,124,199,230], which has the advantage of being relatively cheap and fast to generate at scale compared to human-generated datasets. Finally, there are other types of creators such as non-experts, unspecified individuals, or a broad set of creators (e.g., in the case of web crawled data) [13,228,268,277].…”

Section: Dimensions and Codesmentioning

confidence: 99%

“…For larger datasets (around tens of 1000s of examples) we denote this as large [56,207,257]. For models that undergo extensive large-scale pre-training, we categorized data used in this process as extremely large to indicate a dataset of millions of examples [43,223,228,276] or more. We also included an unknown if the paper did not explicitly mention the dataset used for training [180,192,238].…”

Section: Dimensions and Codesmentioning

confidence: 99%

“…In reinforcement learning (RL), models learn by interacting with an environment and receiving feedback in the form of rewards. This approach is useful for tasks requiring action sequences, such as language generation and dialogue systems [228].…”

Section: Dimensions and Codesmentioning

confidence: 99%

See 2 more Smart Citations

A Design Space for Intelligent and Interactive Writing Assistants

Lee,

Gero,

Chung

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

show abstract

Section: Dimensions and Codesmentioning

confidence: 99%

Section: Dimensions and Codesmentioning

confidence: 99%

See 1 more Smart Citation

A Design Space for Intelligent and Interactive Writing Assistants

Lee,

Gero,

Chung

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…a Note that we did not mention transfer works that shift the styles from one author to the other (e.g.,Syed et al 2020;Singh et al 2021). As opposed to the Shakespeare-Joyce example given above, which is moving texts along some diachronical dimensions and with respect to their poem or poetry nature, these works take style as a persistent characteristics of specific individuals.…”

mentioning

confidence: 99%

From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey

Troiano¹,

Aswathy²,

Klinger³

2021

Preprint

View full text Add to dashboard Cite

Humans are naturally endowed with the ability to write in a particular style. They can, for instance, rephrase a formal letter in an informal way, convey a literal message with the use of figures of speech, edit a novel mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at re-writing existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chat-bots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience. Style transfer has been dedicated several style-aware paraphrasing methods. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them into a hierarchy, highlighting the challenges for the definition of each of them, and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author's personal characteristics. Hence, our review shows how the groups relate to one another, and where specific styles, including some that have never been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.

show abstract

“…alNote that we did not mention transfer works that shift style from one author to the other by including multiple authors (e.g., Syed et al 2020; Singh et al 2021). As opposed to the Shakespeare-Joyce example given above, which paraphrases texts conditioned on a diachronical dimensions and with respect to their poem or poetry nature, these works take style as persistent characteristics of specific individuals.…”

mentioning

confidence: 99%

From theories on styles to their transfer in text: Bridging the gap with a hierarchical survey

2022

View full text Add to dashboard Cite

Humans are naturally endowed with the ability to write in a particular style. They can, for instance, rephrase a formal letter in an informal way, convey a literal message with the use of figures of speech or edit a novel by mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at rewriting existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chatbots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience. Several style-aware paraphrasing methods have attempted to tackle style transfer. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them in a hierarchy, highlighting the challenges for the definition of each of them and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author’s personal characteristics. Hence, our review shows how these groups relate to one another and where specific styles, including some that have not yet been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.

show abstract

DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting

Cited by 5 publications

References 28 publications

A Design Space for Intelligent and Interactive Writing Assistants

A Design Space for Intelligent and Interactive Writing Assistants

From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey

From theories on styles to their transfer in text: Bridging the gap with a hierarchical survey

Contact Info

Product

Resources

About