@article {283, title = {An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition}, journal = {BMC Bioinformatics}, volume = {16}, year = {2015}, pages = {138}, abstract = {

Background This article provides an overview of the first BioASQ challenge, a competition on large-scale biomedical semantic indexing and question answering (QA), which took place between March and September 2013. BioASQ assesses the ability of systems to semantically index very large numbers of biomedical scientific articles, and to return concise and user-understandable answers to given natural language questions by combining information from biomedical articles and ontologies. Results The 2013 BioASQ competition comprised two tasks, Task 1a and Task 1b. In Task 1a participants were asked to automatically annotate new PubMed documents with MeSH headings. Twelve teams participated in Task 1a, with a total of 46 system runs submitted, and one of the teams performing consistently better than the MTI indexer used by NLM to suggest MeSH headings to curators. Task 1b used benchmark datasets containing 29 development and 282 test English questions, along with gold standard (reference) answers, prepared by a team of biomedical experts from around Europe and participants had to automatically produce answers. Three teams participated in Task 1b, with 11 system runs. The BioASQ infrastructure, including benchmark datasets, evaluation mechanisms, and the results of the participants and baseline methods, is publicly available. Conclusions A publicly available evaluation infrastructure for biomedical semantic indexing and QA has been developed, which includes benchmark datasets, and can be used to evaluate systems that: assign MeSH headings to published articles or to English questions; retrieve relevant RDF triples from ontologies, relevant articles and snippets from PubMed Central; produce \“exact\” and paragraph-sized \“ideal\” answers (summaries). The results of the systems that participated in the 2013 BioASQ competition are promising. In Task 1a one of the systems performed consistently better from the NLM\’s MTI indexer. In Task 1b the systems received high scores in the manual evaluation of the \“ideal\” answers; hence, they produced high quality summaries as answers. Overall, BioASQ helped obtain a unified view of how techniques from text classification, semantic indexing, document and passage retrieval, question answering, and text summarization can be combined to allow biomedical experts to obtain concise, user-understandable answers to questions reflecting their real information needs.

}, doi = {10.1186/s12859-015-0564-6}, url = {http://www.biomedcentral.com/content/pdf/s12859-015-0564-6.pdf}, author = {Tsatsaronis, George and Balikas, Georgios and Malakasiotis, Prodromos and Partalas, Ioannis and Zschunke, Matthias and Alvers, Michael R and Weissenborn, Dirk and Krithara, Anastasia and Petridis, Sergios and Polychronopoulos, Dimitris and Almirantis, Yannis and Pavlopoulos, John and Baskiotis, Nicolas and Gallinari, Patrick and Artieres, Thierry and Ngonga, Axel and Heino, Norman and Gaussier, Eric and Barrio-Alvers, Liliana and Schroeder, Michael and Androutsopoulos, Ion and Paliouras, Georgios} }