%0 Journal Article %1 Kolluru2011 %A Kolluru, Balakrishna %A Hawizy, Lezan %A Murray-Rust, Peter %A Tsujii, Junichi %A Ananiadou, Sophia %D 2011 %I Public Library of Science %J PloS one %K *cul named-entity-recognition oscapr text-mining %N 5 %P e20181+ %R 10.1371/journal.pone.0020181 %T Using workflows to explore and optimise named entity recognition for chemistry. %U http://dx.doi.org/10.1371/journal.pone.0020181 %V 6 %X Chemistry text mining tools should be interoperable and adaptable regardless of system-level implementation, installation or even programming issues. We aim to abstract the functionality of these tools from the underlying implementation via reconfigurable workflows for automatically identifying chemical names. To achieve this, we refactored an established named entity recogniser (in the chemistry domain), OSCAR and studied the impact of each component on the net performance. We developed two reconfigurable workflows from OSCAR using an interoperable text mining framework, U-Compare. These workflows can be altered using the drag-&-drop mechanism of the graphical user interface of U-Compare. These workflows also provide a platform to study the relationship between text mining components such as tokenisation and named entity recognition (using maximum entropy Markov model (MEMM) and pattern recognition based classifiers). Results indicate that, for chemistry in particular, eliminating noise generated by tokenisation techniques lead to a slightly better performance than others, in terms of named entity recognition (NER) accuracy. Poor tokenisation translates into poorer input to the classifier components which in turn leads to an increase in Type I or Type II errors, thus, lowering the overall performance. On the Sciborg corpus, the workflow based system, which uses a new tokeniser whilst retaining the same MEMM component, increases the F-score from 82.35\% to 84.44\%. On the PubMed corpus, it recorded an F-score of 84.84\% as against 84.23\% by OSCAR.

@article{Kolluru2011, abstract = {{ Chemistry text mining tools should be interoperable and adaptable regardless of system-level implementation, installation or even programming issues. We aim to abstract the functionality of these tools from the underlying implementation via reconfigurable workflows for automatically identifying chemical names. To achieve this, we refactored an established named entity recogniser (in the chemistry domain), OSCAR and studied the impact of each component on the net performance. We developed two reconfigurable workflows from OSCAR using an interoperable text mining framework, U-Compare. These workflows can be altered using the drag-\&-drop mechanism of the graphical user interface of U-Compare. These workflows also provide a platform to study the relationship between text mining components such as tokenisation and named entity recognition (using maximum entropy Markov model (MEMM) and pattern recognition based classifiers). Results indicate that, for chemistry in particular, eliminating noise generated by tokenisation techniques lead to a slightly better performance than others, in terms of named entity recognition (NER) accuracy. Poor tokenisation translates into poorer input to the classifier components which in turn leads to an increase in Type I or Type II errors, thus, lowering the overall performance. On the Sciborg corpus, the workflow based system, which uses a new tokeniser whilst retaining the same MEMM component, increases the F-score from 82.35\% to 84.44\%. On the PubMed corpus, it recorded an F-score of 84.84\% as against 84.23\% by OSCAR. }}, added-at = {2019-03-11T21:00:05.000+0100}, author = {Kolluru, Balakrishna and Hawizy, Lezan and Murray-Rust, Peter and Tsujii, Junichi and Ananiadou, Sophia}, biburl = {https://www.bibsonomy.org/bibtex/2876972b091ebf278dbf35d237adae2f5/fairybasslet}, citeulike-article-id = {9349185}, citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pone.0020181}, citeulike-linkout-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3102085/}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/21633495}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=21633495}, day = 25, doi = {10.1371/journal.pone.0020181}, interhash = {14bbba415bfbb8306ddd0aae7ce7eb06}, intrahash = {876972b091ebf278dbf35d237adae2f5}, issn = {1932-6203}, journal = {PloS one}, keywords = {*cul named-entity-recognition oscapr text-mining}, month = may, number = 5, pages = {e20181+}, pmcid = {PMC3102085}, pmid = {21633495}, posted-at = {2011-12-22 18:33:31}, priority = {2}, publisher = {Public Library of Science}, timestamp = {2019-03-11T21:06:37.000+0100}, title = {{Using workflows to explore and optimise named entity recognition for chemistry.}}, url = {http://dx.doi.org/10.1371/journal.pone.0020181}, volume = 6, year = 2011 }