Overview of BioNLP’09 Shared Task on Event Extraction

By Jin-Dong Kim, Tomoko Ohta, Sampo Pyysalo, Yoshinobu Kano, Junichi Tsujii. BioNLP@HLT-NAACL, 2009

675 citations recorded by the source corpus.

The paper presents the design and implementation of the BioNLP'09 Shared Task, and reports the final results with analysis. The shared task consists of three sub-tasks, each of which addresses bio-molecular event extraction at a different level of specificity. The data was developed based on the GENIA event corpus. The shared task was run over 12 weeks, drawing initial interest from 42 teams. Of these teams, 24 submitted final results. The evaluation results are encouraging, indicating that state-of-the-art performance is approaching a practically applicable level and revealing some remaining challenges.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/d461edc4de7d4c1398f76c08b54310cd017b963d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

DNorm: disease name normalization with pairwise learning to rank (2013, background): “…named entity recognition (NER) research has received increased attention recently, partly owing to BioCreative (Hirschman et al. , 2005b) and BioNLP (Kim et al. , 2009) challenges on recognition of genes, proteins and biological events in the scientific literature, as well as TREC (Voorhees and…”
A Comprehensive Benchmark of Kernel Methods to Extract Protein–Protein Interactions from Literature (2010, background): “Kernel-based approaches to PPI extraction—and especially those working with convolution kernels — have shown high predictive accuracy and occupied top ranks in relevant CASP-style community challenges [34].”
SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals (2009, background): “roles (Carreras and Màrquez, 2004) or the BioNLP 2009 task (Kim et al., 2009) where negated relations are also labelled as positive.”
Stanford typed dependencies manual (2010, background): “In the recent BioNLP 2009 Shared Task, many of the leading teams built their relation extraction systems over the Stanford Dependency representation (Kim et al. 2009).”
Named Entity Recognition in the Medical Domain with Constrained CRF Models (2017, background): “With respect to our overall objective of entity and relation extraction from the medical literature, a large proportion of the related work originates from BioNLP event extraction (Kim et al., 2009; Nédellec et al., 2013; Chaix et al., 2016; Deléger et al., 2016).”
Overview of BioNLP Shared Task 2013 (2013, methodology): “It was first organized as the sole task of the initial 2009 edition of BioNLP-ST (Kim et al. , 2009).”
Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts (2013, neutral): “So far, state-of-the-art systems for these datasets are mostly supervised ones based on SVM [41] and CRF [8,45].”
Biomedical Event Trigger Identification Using Bidirectional Recurrent Neural Network Based Models (2017, background): “So as to gain attraction among researchers many challenges such as BioNLP’09 (Kim et al., 2009), BioNLP’11 (Kim et al., 2011), BioNLP’13 (N´edellec et al., 2013) have been organized and many novel methods have also been proposed addressing these tasks.”
LINNAEUS: A species name identification system for biomedical literature (2010, background): “In recent text-mining challenges such as the identification of protein-protein-interactions at BioCreative II [8] or bio-molecular event extraction at the BioNLP shared task [9], some groups considered species identification and normalization an essential sub-task [10].”
SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals (2010, methodology): “…Textual Entailment or Information Validation paradigm (Dagan et al., 2006), and in contrast to “aboutness” annotation such as semantic roles (Carreras and Màrquez, 2004; Carreras and Màrquez, 2005) or the BioNLP 2009 task (Kim et al., 2009) where negated relations are also labelled as positive.”
Position-aware Attention and Supervised Data Improve Slot Filling (2017, background): “In addition, the BioNLP Shared Tasks (Kim et al., 2009) are yearly efforts on creating datasets and evaluations for biomedical information extraction systems.”
An adaptive annotation approach for biomedical entity and relation recognition (2016, background): “Medical named entity mention recognition is a well-researched area with a large number of datasets used in competitions [14, 37–40].”
Relation Extraction Using Distant Supervision (2018, methodology): “The authors perform two types of evaluation: on a small but fully annotated dataset called GENIA [28] (containing 800 training and 150 testing instances) and on a set of PubMed12 abstracts where PID [58] was used as a knowledge base.”
Bidirectional RNN for Medical Event Detection in Electronic Health Records (2016, methodology): “Many named entity recognition systems in the biomedical domain have been driven by the Shared tasks of BioNLP (Kim et al., 2009), BioCreAtivE (Hirschman et al., 2005) i2b2 shared NLP tasks (Li et al., 2009) and ShARe/CLEF evaluation tasks (Pradhan et al., 2014”
Bridging semantics and syntax with graph algorithms - state-of-the-art of extracting biomedical relations (2017, methodology): “[125], Pro3Gres Parser [128], Kay Chart Parser [160], C&C [176] Shared Corpora BioNLP-09 event corpus [108], BioNLP-11 event corpus [109], BioNLP-13 event corpus [110], BioCreative-II relation corpus [130], BioCreative-”
The CoNLL-2010 Shared Task: Learning to Detect Hedges and their Scope in Natural Language Text (2010, background): “Several related works have also been published within the framework of The BioNLP’09 Shared Task on Event Extraction (Kim et al., 2009), where a separate subtask was dedicated to predicting whether the recognized biological events are under negation or speculation, based on the GENIA event corpus…”
Deep Learning with Minimal Training Data: TurkuNLP Entry in the BioNLP Shared Task 2016 (2016, background): “The BioNLP Shared Task 2016 was the fourth in the series to focus on event extraction, an information extraction task targeting structured associations of biomedical entities (Kim et al., 2009; Ananiadou et al., 2010).”