Tutorial:

• Natural Language Processing for Intelligent Access to Scientific Information, presented at COLING 2016 (pp. 9-13). Description and slides at: http://taln.upf.edu/pages/coling2016tutorial/

Tools:

• Dr. Inventor Text Mining Framework: a self-contained java library that implements and integrates a wide range of NLP resources for the analysis of scientific publications. More info at: http://driframework.readthedocs.io/
• TextDigester: an open-source text summarization java library that implements several extractive summarization approaches  More info at: https://github.com/fra82/textdigester
• Twitter Crawlers: onpen-source fully-customizable java library to easily retrieve data exploiting Twitter REST and streaming APIs. More info at: https://github.com/fra82/twitter-crawler

More on GitHub at: https://github.com/fra82

Corpora:

• Dr. Inventor Multi-layer Scientific Corpus: corpus of scientific publications manually annotated with respect to several semantic facets of scientific information (scientific discourse, citation purpose, sentence summary relevance). More info at: http://sempub.taln.upf.edu/dricorpus