Automatic Natural Language Style Classification and Transformation

Khosmood, Foaad; Levinson, Robert

doi:10.14236/ewic/irsg2008.3

Cited by 9 publications

(12 citation statements)

References 14 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Back-and-forth machine translation provides a simple but highly limited technique [3,7,10,14,44], as it does not allow targeting or avoiding any particular style. Another classical alternative is rule-based paraphrase replacement from knowledge bases [12, 36-40, 45, 61], 1 https://gitlab.com/ssg-research/mlsec/parchoice/ Techniques Transformations applied [40,46] synonym replacement from WordNet [45,61] word embedding neighbour replacement [38] word replacement from GNU Diction [26], hand-crafted rules [12] synonym replacement from FreeLing [54], hand-crafted rules [36] synonym/hypernym/definition replacement from WordNet or PPDB, hand-crafted rules Table 1. Prior rule-based style transfer techniques.…”

Section: Introductionmentioning

confidence: 99%

Effective writing style transfer via combinatorial paraphrasing

Gröndahl

Asokan

2020

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

Stylometry can be used to profile or deanonymize authors against their will based on writing style. Style transfer provides a defence. Current techniques typically use either encoder-decoder architectures or rule-based algorithms. Crucially, style transfer must reliably retain original semantic content to be actually deployable. We conduct a multifaceted evaluation of three state-of-the-art encoder-decoder style transfer techniques, and show that all fail at semantic retainment. In particular, they do not produce appropriate paraphrases, but only retain original content in the trivial case of exactly reproducing the text. To mitigate this problem we propose ParChoice: a technique based on the combinatorial application of multiple paraphrasing algorithms. ParChoice strongly outperforms the encoder-decoder baselines in semantic retainment. Additionally, compared to baselines that achieve nonnegligible semantic retainment, ParChoice has superior style transfer performance. We also apply ParChoice to multi-author style imitation (not considered by prior work), where we achieve up to 75% imitation success among five authors. Furthermore, when compared to two state-of-the-art rule-based style transfer techniques, ParChoice has markedly better semantic retainment. Combining ParChoice with the best performing rulebased baseline (Mutant-X [34]) also reaches the highest style transfer success on the Brennan-Greenstadt and Extended-Brennan-Greenstadt corpora, with much less impact on original meaning than when using the rulebased baseline techniques alone. Finally, we highlight a critical problem that afflicts all current style transfer techniques: the adversary can use the same technique for thwarting style transfer via adversarial training. We show that adding randomness to style transfer helps to mitigate the effectiveness of adversarial training.

show abstract

Section: Introductionmentioning

confidence: 99%

Effective writing style transfer via combinatorial paraphrasing

Gröndahl

Asokan

2020

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

show abstract

“…Rule-based substitutions Khosmood and Levinson [82] outline a basic model of rule-based style imitation based on grammatical changes. The purpose of the system is to alter the style of a source text until it is maximally close to that of a target corpus.…”

Section: Automatic Obfuscationmentioning

confidence: 99%

“…This Classification-Transformation Loop (CTL) [83] is continued until the stylistic distance is sufficiently close or no more transformations are available. [82] applied the CTL to a US Department of Justice memorandum excerpt, with a part of Orwell's Animal Farm as the target corpus. They used 10 style markers for analysis and comparison, and modified the source text with three transformation rules of de-hyphenation, lexical substitution and acronym expansion.…”

Section: Automatic Obfuscationmentioning

confidence: 99%

Text Analysis in Adversarial Settings

Gröndahl

Asokan

2019

ACM Comput. Surv.

View full text Add to dashboard Cite

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 literature review of existing empirical work, we demonstrate that while certain linguistic features have been indicative of deception in certain corpora, they fail to generalize across divergent semantic domains. We suggest that deceptiveness as such leaves no content-invariant stylistic trace , and textual similarity measures provide a superior means of classifying texts as potentially deceptive. Additionally, we discuss forms of deception beyond semantic content, focusing on hiding author identity by writing style obfuscation . Surveying the literature on both author identification and obfuscation techniques, we conclude that current style transformation methods fail to achieve reliable obfuscation while simultaneously ensuring semantic faithfulness to the original text. We propose that future work in style transformation should pay particular attention to disallowing semantically drastic changes.

show abstract

“…There are other works [8,9] on automatic replacement and style transformation. However, these works either provide a general approach or are not acceptable in practice.…”

Section: Related Workmentioning

confidence: 99%

“…However, these works either provide a general approach or are not acceptable in practice. In [8], it is suggested to transform the writing style of a document incrementally using a loop, where in each run of the loop, the style is slightly changed and this is repeated until some target condition is satisfied. An example of this latter category is [9] where all the words in a document are automatically replaced with their synonyms.…”

Section: Related Workmentioning

confidence: 99%

Secure Obfuscation of Authoring Style

Galib

2015

Information Security Theory and Practice

View full text Add to dashboard Cite

Anonymous authoring includes writing reviews, comments and blogs, using pseudonyms with the general assumption that using these pseudonyms will protect the real identity of authors and allows them to freely express their views. It has been shown, however, that writing style may be used to trace authors across multiple Websites. This is a serious threat to privacy and may even result in revealing the authors's identities. In obfuscating authors' writing style, an authored document is modified to hide the writing characteristics of the author. In this paper we first show that existing obfuscation systems are insecure and propose a general approach for constructing obfuscation algorithms, and then instantiate the framework to give an algorithm that semi-automatically modifies an author's document. We provide a secure obfuscation scheme that is able to hide an author's document securely among other authors' documents in a corpus. As part of our obfuscation algorithm we present a new algorithm for identifying an author's unique words that would be of independent interest. We present a security model and use it to analyze our scheme and also the previous schemes. We implement our scheme and give its performances through experiments. We show that our algorithm can be used to obfuscate documents securely and effectively.

show abstract

Automatic Natural Language Style Classification and Transformation

Cited by 9 publications

References 14 publications

Effective writing style transfer via combinatorial paraphrasing

Effective writing style transfer via combinatorial paraphrasing

Text Analysis in Adversarial Settings

Secure Obfuscation of Authoring Style

Contact Info

Product

Resources

About