MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition.
David Ifeoluwa AdelaniGraham NeubigSebastian RuderShruti RijhwaniMichael BeukmanChester Palen-MichelConstantine LignosJesujoba O. AlabiShamsuddeen Hassan MuhammadPeter NabendeCheikh M. Bamba DioneAndiswa BukulaRooweither MabuyaBonaventure F. P. DossouBlessing K. SibandaHappy BuzaabaJonathan MukiibiGodson KalipeDerguene MbayeAmelia V. TaylorFatoumata Ouoba KaboreChris Chinenye EmezueAremu AnuoluwapoPerez OgayoCatherine GitauEdwin Munkoh-BuabengVictoire Memdjokam KoagneAllahsera Auguste TapoTebogo MacucwaVukosi MarivateElvis MboningTajuddeen GwadabeTosin P. AdewumiOrevaoghene AhiaJoyce Nakatumba-NabendeNeo L. MokonoIgnatius EzeaniChiamaka ChukwunekeMofetoluwa AdeyemiGilles HachemeIdris AbdulmuminOdunayo OgundepoOreen YousufTatiana Moteu NgoliDietrich KlakowPublished in: EMNLP (2022)
Keyphrases
- transfer learning
- named entity recognition
- named entities
- information extraction
- semi supervised
- natural language processing
- labeled data
- knowledge transfer
- learning tasks
- text summarization
- maximum entropy
- text mining
- semi supervised learning
- machine learning
- cross domain
- active learning
- reinforcement learning
- conditional random fields
- domain adaptation
- transfer knowledge
- unlabeled data
- collaborative filtering
- text classification
- annotated corpus
- classifier ensemble
- multi task
- question answering
- feature selection
- target domain