![]() Furthermore, public datasets have not considered these complications and the general semantic annotations are lacking which may result in zero-shot problem. The main challenge is that the dialogue often involves complexity in user’s intents (or purposes) which are multiproned, subject to spontaneous change, and difficult to track. However, preliminary systems have quickly found the inadequacy in relying on simple classification techniques to effectively accomplish the automation task. With the early success of query-answer assistants such as Alexa and Siri, research attempts to expand system capabilities of handling service automation are now abundant. Ting-Wei Wu (Georgia Institute of Technology) Ruolin Su (Georgia Institute of Technology) Biing Juang (Georgia Institute of Technology) We discover temporary spikes in these injustice frames near high-profile shooting events, and finally, we show protest volume correlates with and precedes media framing decisions.Ī Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language Understanding ![]() Liberal sources focus more on the underlying systemic injustice, highlighting the victim’s race and that they were unarmed. Conservative sources emphasize when the victim is armed or attacking an officer and are more likely to mention the victim’s criminal record. Our work uncovers more than a dozen framing devices and reveals significant differences in the way liberal and conservative news sources frame both the issue of police violence and the entities involved. We use it to understand media coverage on police violence in the United States in a new Police Violence Frames Corpus of 82k news articles spanning 7k police killings. We propose an NLP framework to measure entity-centric frames. To Protect and To Serve? Analyzing Entity-Centric Framing of Police ViolenceĬaleb Ziems (Georgia Institute of Technology) Diyi Yang (Georgia Institute of Technology)įraming has significant but subtle effects on public opinion and policy. This dataset will continue to serve as a useful benchmark for understanding this multifaceted issue. We present systematic analyses of our dataset using contemporary baselines to detect and explain implicit hate speech, and we discuss key features that challenge existing models. To fill this gap, this work introduces a theoretically-justified taxonomy of implicit hate speech and a benchmark corpus with fine-grained labels for each message and its implication. Despite much attention being paid to characterize and detect discriminatory speech, most work has focused on explicit or overt hate speech, failing to address a more pervasive form based on coded or indirect language. ![]() Hate speech has grown significantly on social media, causing serious consequences for victims of all demographics. Mai ElSherief (Georgia Institute of Technology) Caleb Ziems (Georgia Institute of Technology) David Muchlinski (Georgia Institute of Technology) Vaishnavi Anupindi (Georgia Institute of Technology) Jordyn Seybolt (Georgia Institute of Technology) Munmun De Choudhury (Georgia Tech) Diyi Yang (Georgia Institute of Technology) Latent Hatred: A Benchmark for Understanding Implicit Hate Speech Computational Social Science and Cultural Analytics
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |