Simple tricks for improving pattern-based information extraction from the biomedical literature.
Simple tricks for improving pattern-based information extraction from the biomedical literature.
复制标题
DOI：
10.1186/2041-1480-1-9
复制
发表时间：
2010-09-24
影响因子：
1.9
通讯作者：
Leser U
中科院分区：
文献类型：
--
作者：
Nguyen QL;Tikk D;Leser U
基于模式的关系抽取方法在生物医学文本挖掘的许多领域都取得了很好的效果。然而，定义正确的模式集是困难的;方法要么是手动的，产生高成本，要么是自动的，通常会导致大量的嘈杂模式。我们提出了几种技术，用于过滤自动生成的模式集，并分析其有效性不同的提取任务，定义在最近的BioNLP 2009年共享任务。我们专注于简单的方法，只考虑模式的复杂性和模式所应用的文本的复杂性。我们表明，我们的技术，尽管它们的简单性，产生很大的改善，我们分析的所有任务。例如，他们将提取基因表达事件任务的F分数从24.8%提高到51.9%。已经非常简单的过滤技术可以显著提高基于自动生成的模式的信息提取方法的F分数。此外，由于需要分析的匹配数量减少，采用这种方法大大加快了速度。由于其简单性，建议的过滤技术也应该适用于其他方法使用语言模式的信息提取。
Pattern-based approaches to relation extraction have shown very good results in many areas of biomedical text mining. However, defining the right set of patterns is difficult; approaches are either manual, incurring high cost, or automatic, often resulting in large sets of noisy patterns. We propose several techniques for filtering sets of automatically generated patterns and analyze their effectiveness for different extraction tasks, as defined in the recent BioNLP 2009 shared task. We focus on simple methods that only take into account the complexity of the pattern and the complexity of the texts the patterns are applied to. We show that our techniques, despite their simplicity, yield large improvements in all tasks we analyzed. For instance, they raise the F-score for the task of extraction gene expression events from 24.8% to 51.9%. Already very simple filtering techniques may improve the F-score of an information extraction method based on automatically generated patterns significantly. Furthermore, the application of such methods yields a considerable speed-up, as fewer matches need to be analysed. Due to their simplicity, the proposed filtering techniques also should be applicable to other methods using linguistic patterns for information extraction.
登录
查看更多内容
影响因子：
3
作者：
Kabiljo R;Clegg AB;Shepherd AJ
通讯作者：
Shepherd AJ
影响因子：
5.8
作者：
Saric, J;Jensen, LJ;Bork, P
通讯作者：
Bork, P
影响因子：
5.8
作者：
Plake, Conrad;Schiemann, Torsten;Leser, Ulf
通讯作者：
Leser, Ulf
DOI：
10.1109/icimw.2009.5324773
发表时间：
2009-01-01
期刊：
METHODS IN BIOENGINEERING: SYSTEMS ANALYSIS OF BIOLOGICAL NETWORKS
影响因子：
--
作者：
Kim, Jin-Hong;Asthagiri, Anand R.
通讯作者：
Asthagiri, Anand R.
影响因子：
3
作者：
Kim JD;Ohta T;Tsujii J
通讯作者：
Tsujii J