Importance of Semantic Representation: Dataless Classification

N/A

Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (2008) Importance of Semantic Representation: Dataless Classification Ming-Wei Chang, Lev Ratinov, Dan Roth and Vivek Srikumar Department of Computer Science University of Illinois at Urbana-Champaign {mchang21, ratinov2, danr, vsrikum2}@uiuc.edu Abstract Using a semantic knowledge…

related reading

• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• 1301.3781arxiv.org
• arxiv.org/pdf/1704.01444arxiv.org
• Learning Unsupervised Visual Grounding Through Semantic Self-Supervisionijcai.org
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelsarxiv.org
• radford2018improving.pdfcs.ubc.ca
• Learning with not Enough Data Part 1: Semi-Supervised Learning | Lil'Loglilianweng.github.io
• DataRater: Meta-Learned Dataset Curationarxiv.org
• [2605.12715] Scaling Laws for Mixture Pretraining Under Data Constraintsarxiv.org
• Learning to Merge Word Sensesaclanthology.org
• Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
• C:\Documents and Settings\nigel\デスクトップ\Cover pages.prn.pdfaclanthology.org