2021/03/17 by Akbar Karimi, Karimi, Akbar, Leonardo Rossi +3
Computer Science · #Advanced Malware Detection Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection
paper · pdf · doi:10.48550/arxiv.2103.09645
openalex publication_date 2021/03/17 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
With the ever-increasing availability of digital information, toxic content\nis also on the rise. Therefore, the detection of this type of language is of\nparamount importance. We tackle this problem utilizing a combination of a\nstate-of-the-art pre-trained language model (CharacterBERT) and a traditional\nbag-of-words technique. Since the content is full of toxic words that have not\nbeen written according to their dictionary spelling, attendance to individual\ncharacters is crucial. Therefore, we use CharacterBERT to extract features\nbased on the word characters. It consists of a CharacterCNN module that learns\ncharacter embeddings from the context. These are, then, fed into the well-known\nBERT architecture. The bag-of-words method, on the other hand, further improves\nupon that by making sure that some frequently used toxic words get labeled\naccordingly. With a 4 percent difference from the first team, our system ranked\n36th in the competition. The code is available for further re-search and\nreproduction of the results.\n