Free Text Gene Name Recognition

1)自2005年以来，我一直是BioCreative研讨会的联合组织者，并参加了BioCreative II(2007)、BioCreative III(2010)、BioCreative-2012研讨会(2012)和BioCreative IV(2013)，我的团队正在参加尚未举行的BioCreative V(2015)。生物创意讲习班的总体目标是促进开发对生物科学研究人员和数据库馆长社区有用的文本挖掘和文本处理工具。 2)我们目前正在努力开发更通用的方法，根据摘要为PPI寻找高价值文章。这一努力不仅涉及更强大的排名方法，还包括向用户显示证据以供用户快速评估的方式。 3)我们还在研究一种对大量生物重要实体类型进行命名实体识别的方法。我们已经发现了某些通用模式，可以用来寻找基因和其他实体类型，其可靠性比普通CRF更高。这是一项正在进行的研究，有望开发出更有用的通用模式。 4)我们已经开始了一个名为Bioc的项目，该项目致力于创建由DTD定义的通用XML格式以及读写该格式的软件。目前，该方法已在C++、Java、Python、PEAR、Ruby和Go中实现。其想法是使用这种通用货币来使对自然语言处理有用的软件模块更具互操作性。该项目还处于早期阶段，但我们已经有了用上述语言读写的软件，以及使用这种方法的重要NLP处理模块，以及以这种格式提供的25个黄金标准NLP注释数据集。该方法在BioCreative IV讲习班上得到了介绍，该方法已成为即将在BioCreative V上举行的Bioc协作轨道的基础。除了我们自己的团队外，这个赛道还收到了八个团队的贡献，并建立了一个用户界面，向Bioggrid策展人展示带注释的文章，以协助他们的工作。

1) I have been a co-organizer of the BioCreative Workshops since 2005 and have taken part in BioCreative II (2007), BioCreative III (2010), BioCreative-2012 Workshop (2012), and BioCreative IV (2013) and my group is taking part in BioCreative V (2015) which has not yet taken place. The overall goal of the BioCreative Workshops is to promote the development of text mining and text processing tools which are useful to the communities of researchers and database curators in the biological sciences. 2) We are currently working to develop more general methods of finding high value articles for PPI based on their abstracts. This effort involves not only more powerful ranking methods, but also ways to display evidence to the user for a users quick evaluation. 3) We are also investigating an approach to named entity recognition for a large number of biologically important entity types. We have found certain general patterns that can be used to find genes and other entity types with a higher reliability than can be done with a general CRF. This is ongoing research with a promise for more useful general patterns. 4) We have begun a project called BioC which is an effort to create a general XML format defined by a DTD and software to read and write this format. Currently this approach has been implemented in C++, Java, Python, Pearl, Ruby, and GO. The idea is to use this common currency to make software modules that are useful for natural language processing more interoperable. The project is in its early stages, but already we have software to read and write in the languages mentioned as well as significant NLP processing modules using this approach and over 25 gold standard NLP annotated data sets available in the format. The approach was featured in the BioCreative IV Workshop and the approach has formed the basis of the BioC Collaborative Track at BioCreative V which will take place in a short time. This track has received contributions from eight teams besides our own and has built a user interface which displays annotated articles to Biogrid curators to assist them in their work.