GENIA corpus version 3.0 consisting of 2000 MEDLINE abstracts has been released with more than 400,000 words and almost 100,000 annotations for biological terms.

The paper presents the design and implementation of the BioNLP'09 Shared Task, and reports the final results with analysis. The shared task consists of three sub-tasks, each of which addresses bio-molecular event extraction at a different level of specificity. The data was developed based on the GENIA event corpus. The shared task was run over 12 weeks, drawing initial interest from 42 teams. Of these teams, 24 submitted final results. The evaluation results are encouraging, indicating that state-of-the-art performance is approaching a practically applicable level and revealing some remaining challenges.

Background: Advanced Text Mining (TM) such as semantic enrichment of papers, event or relation extraction, and intelligent Question Answering have increasingly attracted attention in the bio-medical domain. For such attempts to succeed, text annotation from the biological point of view is indispensable. However, due to the complexity of the task, semantic annotation has never been tried on a large scale, apart from relatively simple term annotation.

No abstract

This paper defines a generative probabilistic model of parse trees, which we call PCFG-LA. This model is an extension of PCFG in which non-terminal symbols are augmented with latent variables. Finegrained CFG rules are automatically induced from a parsed corpus by training a PCFG-LA model using an EM-algorithm. Because exact parsing with a PCFG-LA is NP-hard, several approximations are described and empirically compared. In experiments using the Penn WSJ corpus, our automatically trained model gave a performance of 86.6% (F¥ , sentences ¦ 40 words), which is comparable to that of an unlexicalized PCFG parser created using extensive manual feature selection.

We explore the use of Support Vector Machines (SVMs) for biomedical named entity recognition. To make the SVM training with the available largest corpus -the GENIA corpus -tractable, we propose to split the non-entity class into sub-classes, using part-of-speech information. In addition, we explore new features such as word cache and the states of an HMM trained by unsupervised learning. Experiments on the GENIA corpus show that our class splitting technique not only enables the training with the GENIA corpus but also improves the accuracy. The proposed new features also contribute to improve the accuracy. We compare our SVMbased recognition system with a system using Maximum Entropy tagging method.

No abstract

\~e report the results of a study into the use of a linear interpolating hidden Marker model (HMM) for the task of extra.('ting lxw]mi(:al |;erminology fl:om MEDLINE al)stra('ts and texl;s in the molecular-bioh)gy domain. Tiffs is the first stage isl a. system that will exl;ra('l; evenl; information for automatically ut)da.ting 1)ioh)gy databases. We trained the HMM entirely with 1)igrams based (m lexical and character features in a relatively small corpus of 100 MED-LINE abstract;s that were ma.rked-ul) l)y (lomain experts wil;h term (:lasses su(:h as t)rol;eins and DNA. I.Jsing cross-validation methods we a(:]fieved a,n ].e-score of 0.73 and we (',xmnine the ('ontrilmtion made by each 1)art of the interl)olation model to overconfing (la.ta Sl)arsen('.ss.