10.9k citations
- Massachusetts Institute of TechnologyUS270 papers
- Harvard UniversityUS238 papers
- The Ohio State UniversityUS186 papers
- Lawrence Berkeley National LaboratoryUS185 papers
- University of OxfordGB176 papers
- University of PisaIT169 papers
- University of ChicagoUS168 papers
- University of LiverpoolGB167 papers
- University of MichiganUS166 papers
- Sapienza University of RomeIT165 papers
- Yale UniversityUS160 papers
- University of Wisconsin–MadisonUS155 papers
5 papers · 2 filters
Detecting Hate Speech in Social Media
Shervin Malmasi, Marcos Zampieri
In this paper we examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by app…
Complex Word Identification: Challenges in Data Annotation and System Performance
Marcos Zampieri, Shervin Malmasi, Gustavo Paetzold +1
This paper revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational met…
Language Modeling by Clustering with Word Embeddings for Text Readability Assessment
Miriam Cha, Youngjune Gwon, H. T. Kung
We present a clustering-based language model using word embeddings for text readability prediction. Presumably, an Euclidean semantic space hypothesis holds true for word embedding…
Learning opacity in Stratal Maximum Entropy Grammar
Aleksei Nazarov, Joe Pater
Opaque phonological patterns are sometimes claimed to be difficult to learn; specific hypotheses have been advanced about the relative difficulty of particular kinds of opaque proc…
Structured Attention Networks
Yoon Kim, Carl Denton, Luong Hoang +1
Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer str…