ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation

Xu, Qiongkai; Xu, Chenchen; Qu, Lizhen

doi:10.18653/v1/d19-3003

Cited by 7 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[Shang et al 2015] criou uma rede neural treinada sobre textos coletados de um serviço de microblog, semelhante ao Twitter, para geração de respostas em textos curtos, para conversação, capaz de gerar frases gramaticalmente corretas. [Xu et al 2019] propõe uma ferramenta para auxiliar na reescrita de textos e tarefas de geração de linguagem natural. [Goldfarb-Tarrant et al 2019] propôs um sistema interativo entre humano e computador capaz de auxiliar na escrita de histórias.…”

Section: Trabalhos Relacionadosunclassified

Um estudo sobre o aprimoramento de tuítes com base na substituição de adjetivos

Pasa

Oliveira

Mergen

2021

Anais Da XVI Escola Regional De Banco De Dados (ERBD 2021)

View full text Add to dashboard Cite

Hoje em dia, redes sociais como o Twitter são usadas não apenas para entretenimento, mas como uma ferramenta de trabalho, seja de cunho político, artístico ou puramente comercial. Muitas das mensagens publicadas são concebidas com cuidado, de modo a fidelizar e ampliar a base de seguidores. Nesse contexto, este trabalho propõe a reescrita de tuítes visando aumentar o seu engajamento. A reescrita proposta substitui adjetivos por sinônimos considerados mais adequados, levando em consideração os adjetivos que são comumente associados à tuítes com alta taxa de engajamento. Os resultados experimentais usando um algoritmo de aprendizado de máquina como avaliador demonstram que o processo de reescrita potencialmente gera tuítes melhores.

show abstract

Section: Trabalhos Relacionadosunclassified

Um estudo sobre o aprimoramento de tuítes com base na substituição de adjetivos

Pasa

Oliveira

Mergen

2021

Anais Da XVI Escola Regional De Banco De Dados (ERBD 2021)

View full text Add to dashboard Cite

show abstract

“…The performances of those tasks have improved significantly in the last several years due to the advance of deep learning technologies and the availability of large scale training data. The models we proposed in this paper are motivated by these prior research work, especially the recent advances [8,10,17,18,23]. However, the goal of our new rewriting task is different: we are focusing on extending and enriching a user's input so that it's more attractive.…”

Section: Related Workmentioning

confidence: 99%

Visual Question Rewriting for Increasing Response Rate

Wei

Zhang

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

When a human asks questions online, or when a conversational virtual agent asks a human questions, questions triggering emotions or with details might more likely to get responses or answers. we explore how to automatically rewrite natural language questions to improve the response rate form people. In particular, a new task of Visual Question Rewriting (VQR) task is introduced to explore how visual information can be used to improve the new question(s). A data set containing ∼4K bland&attractive question-images triples is collected. We developed some baseline sequence to sequence models and more advanced transformer-based models, which take a bland question and a related image as input, and output a rewritten question that's expected to be more attractive. Offline experiments and mechanical Turk based evaluations show that it's possible to rewrite bland questions in a more detailed and attractive way to increase response rate, and images can be helpful. CCS CONCEPTS• Computing methodologies → Natural language processing; Computer vision.

show abstract

“…The need to collect attribute-specific re-writes further motivated Xu et al (2019a) to create ALTER. As a publicly available tool c , ALTER was developed to overcome one major pitfall of crowdsourcing when it comes to generating gold standards: human annotators might fail to associate textual patterns to a gender label, at least when dealing with short pieces of text.…”

Section: Gender and Agementioning

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

ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation

Cited by 7 publications

References 12 publications

Um estudo sobre o aprimoramento de tuítes com base na substituição de adjetivos

Um estudo sobre o aprimoramento de tuítes com base na substituição de adjetivos

Visual Question Rewriting for Increasing Response Rate

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

Contact Info

Product

Resources

About