arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.01043cs.CL
收藏

用于滥用语言检测的神经词分解模型

Neural Word Decomposition Models for Abusive Language Detection

Amazon AI(亚马逊人工智能)

Sravan Babu Bodapati, Spandana Gella, Kasturi Bhattacharjee, Yaser Al-Onaizan

摘要:

社交媒体上的用户生成文本通常具有许多不受欢迎的特征,包括仇恨言论,辱骂性语言,侮辱等,这些特征旨在攻击或虐待特定人群。通常,与传统文本相比,这样的文本被不同地书写,传统文本诸如涉及明确提及辱骂性词语、混淆词语和类型错误或隐含辱骂的新闻,即,表明或针对消极的刻板印象。因此,当我们应用为传统文本开发的自然语言处理技术时,处理此文本提出了几个鲁棒性挑战。例如,使用基于单词或标记的模型来处理这样的文本可以将单词的两个拼写变体视为两个不同的单词。根据最近的工作,我们分析了字符,子字和字节对编码(BPE)模型可以帮助用户生成的文本所带来的一些挑战。在我们的工作中,我们分析了上述每种技术的有效性,比较和对比各种词分解技术与其他技术结合使用时。我们尝试微调大型预训练语言模型,并通过研究维基百科攻击,毒性和Twitter仇恨言论数据集来证明它们对域转移的鲁棒性

英文摘要:

User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written differently compared to traditional text such as news involving either explicit mention of abusive words, obfuscated words and typological errors or implicit abuse i.e., indicating or targeting negative stereotypes. Thus, processing this text poses several robustness challenges when we apply natural language processing techniques developed for traditional text. For example, using word or token based models to process such text can treat two spelling variants of a word as two different words. Following recent work, we analyze how character, subword and byte pair encoding (BPE) models can be aid some of the challenges posed by user generated text. In our work, we analyze the effectiveness of each of the above techniques, compare and contrast various word decomposition techniques when used in combination with others. We experiment with finetuning large pretrained language models, and demonstrate their robustness to domain shift by studying Wikipedia attack, toxicity and Twitter hatespeech datasets

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑