Feb. 13, 2024, 5:49 a.m. | Sourabrata Mukherjee Akanksha Bansal Atul Kr. Ojha John P. McCrae Ond\v{r}ej Du\v{s}ek

cs.CL updates on arXiv.org arxiv.org

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where the text style changes while its content is preserved. We present three approaches: knowledge transfer from a similar task, multi-task learning approach, combining sequence-to-sequence modeling with various toxicity classification tasks, and, delete and reconstruct approach. To support our research, we utilize a dataset provided by …

communication cs.cl english hindi knowledge paper style style transfer text text style transfer transfer

Research Scholar (Technical Research)

@ Centre for the Governance of AI | Hybrid; Oxford, UK

HPC Engineer (x/f/m) - DACH

@ Meshcapade GmbH | Remote, Germany

Machine Learning Engineer

@ Verneek | New York City, United States

Principal Data Sciences

@ Target | Tower 02, Manyata Embassy Business Park, Racenahali & Nagawara Villages. Outer Ring Rd, Bengaluru 540065

Analytics Engineer Intern

@ Proekspert | Tallinn, Estonia

Ecologist III (Wetland Scientist III)

@ AECOM | Pittsburgh, PA, United States