Abstract
BackgroundBiomedical event extraction has attracted substantial attention as it can assist researchers in understanding the plethora of interactions among genes that are described in publications in molecular biology. While most recent work has focused on abstracts, the BioNLP 2011 shared task evaluated the submitted systems on both abstracts and full papers. In this article, we describe our submission to the shared task which decomposes event extraction into a set of classification tasks that can be learned either independently or jointly using the search-based structured prediction framework. Our intention is to explore how these two learning paradigms compare in the context of the shared task.ResultsWe report that models learned using search-based structured prediction exceed the accuracy of independently learned classifiers by 8.3 points in F-score, with the gains being more pronounced on the more complex Regulation events (13.23 points). Furthermore, we show how the trade-off between recall and precision can be adjusted in both learning paradigms and that search-based structured prediction achieves better recall at all precision points. Finally, we report on experiments with a simple domain-adaptation method, resulting in the second-best performance achieved by a single system.ConclusionsWe demonstrate that joint inference using the search-based structured prediction framework can achieve better performance than independently learned classifiers, thus demonstrating the potential of this learning paradigm for event extraction and other similarly complex information-extraction tasks.
Highlights
Biomedical event extraction has attracted substantial attention as it can assist researchers in understanding the plethora of interactions among genes that are described in publications in molecular biology
We decompose event extraction into a set of classification tasks that can be learned either independently or jointly using the search-based structured prediction framework (SEARN) [4] in a formulation we proposed in earlier work [5]
Results we compare the event extraction accuracy achieved by the system based on independently learned classifiers versus the accuracy achieved by the system learning classifiers under SEARN
Summary
Biomedical event extraction has attracted substantial attention as it can assist researchers in understanding the plethora of interactions among genes that are described in publications in molecular biology. We describe our submission to the shared task which decomposes event extraction into a set of classification tasks that can be learned either independently or jointly using the search-based structured prediction framework. We decompose event extraction into a set of classification tasks that can be learned either independently or jointly using the search-based structured prediction framework (SEARN) [4] in a formulation we proposed in earlier work [5]. Compared to independently learned classifiers, SEARN is able to achieve better performance because its models are learned jointly. Each of these models is able to incorporate features representing predictions made by the other ones, while taking into account possible mistakes made. We report on experiments with the simple domain adaptation method proposed by Daumé III [7], which creates a version of each feature for each domain
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.