Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora

Kruengkrai, Canasai

doi:10.18653/v1/d19-1659

Cited by 6 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Arguing that superior performance is observed for any sequence-to-sequence task with parallel data, Cavalin et al (2020) employed a semantic similarity measure to derive parallel data from (non-parallel) Amazon and Yelp reviews. Also, Jin et al (2019) and Kruengkrai (2019) derived a pseudo-parallel corpus from mono-style data by aligning semantically similar sentences from the sides of the source and target attributes. For a subset of the Yelp reviews, they collected human-generated styled variations p…”

Section: Intended Stylesmentioning

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

Section: Intended Stylesmentioning

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

show abstract

“…Arguing that superior performance is observed for any sequence-to-sequence task with parallel data, Cavalin et al (2020) employed a semantic similarity measure to derive parallel data from non-parallel ones which consisted of Amazon and Yelp reviews. Also Jin et al (2019) and Kruengkrai (2019) derived a pseudo-parallel corpus from mono-style data by aligning semantically similar sentences from source and target attribute sides. For a subset of the Yelp reviews, they collected human-generated styled variations d .…”

Section: Sentimentmentioning

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

“…Most methods either rely on adversarial objectives (Shen et al, 2017;Hu et al, 2017;Fu et al, 2018), retrieval (Li et al, 2018), or backtranslation (Lample et al, 2019;Logeswaran et al, 2018) to make the latent codes independent of the style attribute. Notable exceptions are Transformer-based Sudhakar et al, 2019), use reinforcement learning for backtranslating through the discrete space , build pseudo-parallel corpora (Kruengkrai, 2019;Jin et al, 2019), or modify the latent-variable at inference time by following the gradient of a style classifier (Wang et al, 2019;Liu et al, 2020). Similar to our motivation, Li et al (2019) aim at improving in-domain performance by incorporating out-of-domain data into training.…”

Section: Related Workmentioning

confidence: 99%

UNICITY: A depth maps database for people detection in security airlocks

Dumoulin

Canévet

Villamizar

et al. 2018

2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the autoencoder's embedding space, training embedding-to-embedding (Emb2Emb). This reduces the need for labeled training data for the task and makes the training procedure more efficient. Crucial to the success of this method is a loss term for keeping the mapped embedding on the manifold of the autoencoder and a mapping which is trained to navigate the manifold by learning offset vectors. Evaluations on style transfer tasks both with and without sequence-to-sequence supervision show that our method performs better than or comparable to strong baselines while being up to four times faster.

show abstract

Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora

Cited by 6 publications

References 16 publications

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

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

UNICITY: A depth maps database for people detection in security airlocks

Contact Info

Product

Resources

About