Cascaded classifiers for confidence-based chemical named entity recognition.
Cascaded classifiers for confidence-based chemical named entity recognition.
复制标题
DOI：
10.1186/1471-2105-9-s11-s4
复制
发表时间：
2008-11-19
影响因子：
3
通讯作者：
Copestake A
中科院分区：
文献类型：
--
作者：
Corbett P;Copestake A
化学命名实体代表了生物医学文本的一个重要方面。我们开发了一个系统，使用基于字符的n-grams，最大熵马尔可夫模型和评分来识别化学名称和其他此类实体，并对提取的实体进行置信度估计。一个可调节的阈值允许系统调整到高精度或高召回。在平衡精度和召回率的阈值设置下，我们能够从化学论文和PubMed摘要中提取命名实体，F值分别为80.7%和83.2%。此外，我们能够在95%查全率下实现57.6%和60.3%的查全率，在90%查全率下实现58.9%和49.1%的查全率。这些结果表明，化学命名实体可以以良好的性能提取，并且可以调整提取的性质以适应任务的要求。
Chemical named entities represent an important facet of biomedical text. We have developed a system to use character-based n-grams, Maximum Entropy Markov Models and rescoring to recognise chemical names and other such entities, and to make confidence estimates for the extracted entities. An adjustable threshold allows the system to be tuned to high precision or high recall. At a threshold set for balanced precision and recall, we were able to extract named entities at an F score of 80.7% from chemistry papers and 83.2% from PubMed abstracts. Furthermore, we were able to achieve 57.6% and 60.3% recall at 95% precision, and 58.9% and 49.1% precision at 90% recall. These results show that chemical named entities can be extracted with good performance, and that the properties of the extraction can be tuned to suit the demands of the task.