Free Text Gene Name Recognition

1)我们已经确信，关于MEDLINE中句子中可能出现的不同类型实体的更多信息可以用于改善姓名识别。这导致我们设计了一套语义类别，并试图用可以从数据库和网站获得的实际名称填充这些类别。我们称结果为SEMCAT。它目前识别75个类别，包含分布在这些类别中的大约400万个名称字符串。我们已经使用概率上下文无关文法和文本串的马尔可夫模型进行了实验，试图学习如何识别不同类别的实体。然而，我们找到的区分基因/蛋白质和非基因/蛋白质类别的最好方法是一种新的算法，我们称之为优先模型。与SEMCAT中的任何名称关联的每个令牌都有两个关联的概率。第一个概率是令牌指示它是基因/蛋白质名称的一部分的概率，第二个概率是令牌作为指示符的可靠性的指示符。利用这个模型，给定一个短语，就可以计算出该阶段是一个基因/蛋白质名称的概率的估计值。我们发现，使用优先级模型，我们可以获得96%的F分数，而我们最好的PCFG方法的F分数为95%。(与Lorrie Tanabe) 在BioCreative II中，基因提及识别的表现最好的是来自IBM的Rie Ando，他引入了一种称为交替结构优化的技术。这种方法处理了许多类似于命名实体标记的标记问题，但只是尝试根据周围的文本上下文预测名称或标记的出现。当学习了这些辅助问题的支持向量解的权重向量时，执行奇异值分解，并从每个向量中减去分解中的前h个分量。该减法仅用于减少成本函数的正则化项中的惩罚。然后重新学习权重向量，并重复该过程。这将一直持续到收敛。最终结果是许多权重向量的分解的h个分量的集合。使用这些组件来增强对实际命名实体识别任务的学习。这有点复杂，很难使用。我们正在研究如何能够使用类似的方法，但使用一种更简单的方法来应用辅助学习来改善命名实体识别。一个问题是如何将这种辅助学习与SEMCAT数据结合起来。我们目前正在努力改进这个模型，找到一种方法将它同时应用到两个以上的班级。 2)我们最近联合主持了BioCreative III研讨会，在该研讨会中，主要竞争任务是在全文文章中查找提到基因的内容，并将其映射到其GenBank标识符并根据可靠性对其进行评分，将PubMed记录归类为可能代表包含蛋白质-蛋白质相互作用信息的文章，以及在全文中找到描述实验人员用来验证蛋白质-蛋白质相互作用的方法的文本。我们组织了第一项任务，并参与了第二项任务。在第二个任务中，我们使用优先级模型来定位蛋白质提及，它被证明是非常成功的，与其他方法相比具有竞争力。 3)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。

1) We have become convinced that more information about the different types of entities that can occur in sentences in MEDLINE can be used to improve name recognition. This has led us to design a set of semantic categories and to attempt to fill these categories with actual names that can be harvested from databases and from web sites. We call the result SEMCAT. It currently recognizes seventy-five categories and contains about four million name strings distributed over those categories. We have experimented with probabilistic context free grammars and Markov models of text strings in an attempt to learn how to recognize the entities in different categories. However, the best approach we have found for distinguishing the categories of gene/protein and not gene/protein is a new algorithm we term a priority model. Every token associated with any name in SEMCAT has associated with it two probabilities. The first probability is the probability that the token indicates that it is part of a gene/protein name and the second probability is an indicator of how reliable the token is as an indicator. With this model, given a phrase, one can compute an estimate of the probability that the phase is a gene/protein name. We find that with the priority model we can achieve an F score of 96% as compared with 95% for our best PCFG approach. (with Lorrie Tanabe). The top performance for gene mention recognition in BioCreative II was by Rie Ando from IBM who introduced a technique called alternating structural optimization. This approach takes many labeling problems similar to named entity tagging, but simply tries to predict the occurrence of the names or the tokens from the surrounding textual context. When the SVM solution weight vectors for these many auxiliary problems have been learned, one performs a singular value decomposition and subtracts from each vector its first h components in the decomposition. This subtraction is only used to decrease the penalty in the regularization term of the cost function. The weight vectors are then relearned and the process is repeated. This is continued until convergence. The final result is a set of h components of the decomposition of the many weight vectors. One uses these components to enhance the learning on the actual named entity recognition task. This is a bit complicated and difficult to use. We are studying how we may be able to use a similar approach, but with a simpler method of applying the auxiliary learning to improve named entity recognition. One problem is how to combine such auxiliary learning with the SEMCAT data. We are currently working to improve this model by finding a way to apply it to more than two classes at a time. 2)We recently co-chaired the BioCreative III Workshop in which the main competitive tasks were to find gene mentions in a full text article and map them to their GenBank identifiers and score them as to reliability, to classify PubMed records as likely to represent articles containing information on protein-protein interactions, and to find the text in full papers that describes the method used by an experimenter to experimentally verify a protein-protein interaction. We organized the first of these task and participated in the second. In the second task we used the priority model to locate protein mentions and it proved very successful and competitive with other approaches. 3) 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.