Slides from 'Stay Calm & Keep Current' - How to filter machine learning related academic papers - introduction of our open source project for this purpose.
13. DataBase Wrapper
Centrifuge - NLP Engine
Web Crawler + Content Scraper
Text Extractor
Readability PDF2Text
DocumentUser
Topic Modeling
Newsletter
Recommender System
Preprocessing
Summarization
Message
Broker
Web-App Facade
Relation
(GraphDB)
14. Centrifuge - Information Filtering Engine
github.com/Keep-Current/Engine
● Topic / Keywords Extraction
○ TF-IDF
○ TextRank / RAKE / TAKE Ensemble
Pay, Tayfun, and Stephen Lucci. "Automatic keyword extraction: An ensemble method." Big Data (Big Data), 2017 IEEE
International Conference on. IEEE, 2017.
● Probabilistic Topic Modeling
○ LDA
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-
1022.
15. Centrifuge - Information Filtering Engine
● Recommender System
○ Proximity Measurement
■ Word Embedding - Doc2Vec
○ Collaborative Filtering (CF)
C. Wang and D. Blei. Collaborative topic modeling for recommending scientific articles. In SIGKDD, pages
448–456. ACM, 2011.
○ Contextual Bandits
Li, L., Chu, W., Langford, J., Schapire, R.E.: A contextual-bandit approach to personalized news article
recommendation. In: Proceedings of the 19th international conference on World Wide Web, ACM (2010) 661–670
17. Roadmap :: Model Rationalization
● LIME
Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. "Why should i trust you?: Explaining the predictions of any
classifier." Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM,
2016.
● Reasoning
○ Lei, Tao, Regina Barzilay, and Tommi Jaakkola. "Rationalizing neural predictions." arXiv preprint arXiv:1606.04155
(2016).
○ Janner, Michael, Karthik Narasimhan, and Regina Barzilay. "Representation learning for grounded spatial
reasoning." arXiv preprint arXiv:1707.03938 (2017).