Towards Aspect Extraction and Classification for Opinion Mining with Deep Sequence Networks

Kersting, Joschka; Geierhos, Michaela

doi:10.1007/978-3-030-63787-3_6

Cited by 3 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After years of considerable progress in Natural Language Processing (NLP), there are still some areas of interest with unsolved challenges. These mainly concern the hand-crafted tasks that still have to be done to obtain better results (e.g., Kersting/Geierhos 2021). Examples include legal issues such as reviewing long contract documents, or domain-specific text generation, summarization, and paraphrasing.…”

Section: Introductionmentioning

confidence: 99%

In Other Words: A Naive Approach to Text Spinning

Bäumer¹,

Kersting²,

Denisov³

et al. 2021

Proceedings of the International Conferences on WWW/Internet 2021 and Applied Computing 2021

View full text Add to dashboard Cite

Content is the new oil. Users consume billions of terabytes a day while surfing on news sites or blogs, posting on social media sites, and sending chat messages around the globe. While content is heterogeneous, the dominant form of web content is text. There are situations where more diversity needs to be introduced into text content, for example, to reuse it on websites or to allow a chatbot to base its models on the information conveyed rather than of the language used. In order to achieve this, paraphrasing techniques have been developed: One example is Text spinning, a technique that automatically paraphrases text while leaving the intent intact. This makes it easier to reuse content, or to change the language generated by the bot more human. One method for modifying texts is a combination of translation and back-translation. This paper presents NATTS, a naive approach that uses transformer-based translation models to create diversified text, combining translation steps in one model. An advantage of this approach is that it can be fine-tuned and handle technical language.

show abstract

Section: Introductionmentioning

confidence: 99%