Semantic Assistants for wikis are our novel architecture for the integration of Natural Language Processing (NLP) capabilities into wiki systems, based on the Semantic Assistants framework. The vision is that of a new generation of wikis that can help developing their own primary content and organize their structure by using state-of-the-art technologies from the NLP and Semantic Computing domains. The motivation for this integration is to enable wiki users – novice or expert – to benefit from modern text mining techniques directly within their wiki environment.

Researchers need to extract and manage critical knowledge from the massive amount of literature available in multiple and ever-growing repositories. The sheer volume of information makes the exhaustive analysis of literature a labor-intensive and time-consuming task, during which significant knowledge can be easily missed. We present IntelliGenWiki, a service-oriented solution that combines state-of-the-art techniques from the Natural Language Processing (NLP) and Semantic Web domains to support the knowledge discovery workflow in omics sciences.

ReqWiki is a novel open source web-based approach for software requirements engineering. It is based on a semantic wiki that includes natural language processing (NLP) assistants, which work collaboratively with humans on the requirements specification documents. It is the first Requirements Engineering tool that combines wiki technology for collaborative use and semantic knowledge representation for formal queries and reasoning with natural language processing assistants within a single, cohesive interface.

Natural Language Processing (NLP) for Software Engineering: Our Eclipse plug-in integrates the Eclipse development environment into the Semantic Assistants architecture. It provides a user interface for offering various Natural Language Processing services to users. In particular, when using Eclipse as a software development environment, you can now offer novel semantic analysis services, such as named entity detection or quality analysis of source code comments, to software developers.

Our open source OrganismTagger is a hybrid rule-based/machine-learning system that extracts organism mentions from the biomedical literature, normalizes them to their scientific name, and provides grounding to the NCBI Taxonomy database. Our pipeline provides the flexibility of annotating the species of particular interest to bio-engineers on different corpora, by optionally including detection of common names, acronyms, and strains. The OrganismTagger performance has been evaluated on two manually annotated corpora, OT and Linneaus. On the OT corpus, the OrganismTagger achieves a precision and recall of 95% and 94% and a grounding accuracy of 97.5%. On the manually annotated corpus of Linneaus-100, the results show a precision and recall of 99% and 97% and grounding with an accuracy of 97.4%. It is described in detail in our publication, Naderi, N., T. Kappler, C. J. O. Baker, and R. Witte, "OrganismTagger: Detection, normalization, and grounding of organism entities in biomedical documents", Bioinformatics, vol. 27, no. 19 Oxford University Press, pp. 2721--2729, August 9, 2011.

We now have a public Jenkins server (formerly known as Hudson) available for our Semantic Assistants project that supports the SourceForge code repository.

In the spirit of continuous integration, every check-in to the Subversion repository is built automatically and additionally checked with various tools. The latest build is archived and available for browsing and download.