ABSTRACT
BACKGROUND: Named Entity Recognition (NER) and Normalisation (NEN) are core components of any text-mining system for biomedical texts. In a traditional concept-recognition pipeline, these tasks are combined in a serial way, which is inherently prone to error propagation from NER to NEN. We propose a parallel architecture, where both NER and NEN are modeled as a sequence-labeling task, operating directly on the source text. We examine different harmonisation strategies for merging the predictions of the two classifiers into a single output sequence. RESULTS: We test our approach on the recent Version 4 of the CRAFT corpus. In all 20 annotation sets of the concept-annotation task, our system outperforms the pipeline system reported as a baseline in the CRAFT shared task, a competition of the BioNLP Open Shared Tasks 2019. We further refine the systems from the shared task by optimising the harmonisation strategy separately for each annotation set. CONCLUSIONS: Our analysis shows that the strengths of the two classifiers can be combined in a fruitful way. However, prediction harmonisation requires individual calibration on a development set for each annotation set. This allows achieving a good trade-off between established knowledge (training set) and novel information (unseen concepts).
Subject(s)
Data MiningABSTRACT
BACKGROUND: Animal health data recorded in free text, such as in necropsy reports, can have valuable information for national surveillance systems. However, these data are rarely utilized because the text format requires labor-intensive classification of records before they can be analyzed with using statistical or other software. In a previous study, we designed a text-mining tool to extract data from text in necropsy reports. In the current study, we used the tool to extract data from the reports from pig and cattle necropsies performed between 2000 and 2011 at the Institute of Animal Pathology (ITPA), University of Bern, Switzerland. We evaluated data quality in terms of credibility, completeness and representativeness of the Swiss pig and cattle populations. RESULTS: Data was easily extracted from necropsy reports. Data quality in terms of completeness and validity varied a lot depending on the type of data reported. Diseases of the gastrointestinal system were reported most frequently (54.6% of pig submissions and 40.8% of cattle submissions). Diseases affecting serous membranes were reported in 16.0% of necropsied pigs and 27.6% of cattle. Respiratory diseases were reported in 18.3% of pigs and 21.6% of cattle submissions. CONCLUSIONS: This study suggests that extracting data from necropsy reports can provide information of value for animal health surveillance. This data has potential value for monitoring endemic disease syndromes in different age and production groups, or for early detection of emerging or re-emerging diseases. The study identified data entry and other errors that could be corrected to improve the quality and validity of the data. Submissions to veterinary diagnostic laboratories have selection biases and these should be considered when designing surveillance systems that include necropsy reports.
Subject(s)
Autopsy/veterinary , Cattle Diseases/pathology , Data Mining , Health Status Indicators , Swine Diseases/pathology , Animals , Cattle , Female , Health Surveys , Information Storage and Retrieval , Male , Software , Swine , SyndromeABSTRACT
BACKGROUND: We present a text-mining tool for recognizing biomedical entities in scientific literature. OGER++ is a hybrid system for named entity recognition and concept recognition (linking), which combines a dictionary-based annotator with a corpus-based disambiguation component. The annotator uses an efficient look-up strategy combined with a normalization method for matching spelling variants. The disambiguation classifier is implemented as a feed-forward neural network which acts as a postfilter to the previous step. RESULTS: We evaluated the system in terms of processing speed and annotation quality. In the speed benchmarks, the OGER++ web service processes 9.7 abstracts or 0.9 full-text documents per second. On the CRAFT corpus, we achieved 71.4% and 56.7% F1 for named entity recognition and concept recognition, respectively. CONCLUSIONS: Combining knowledge-based and data-driven components allows creating a system with competitive performance in biomedical text mining.
ABSTRACT
BACKGROUND: This article describes a high-recall, high-precision approach for the extraction of biomedical entities from scientific articles. METHOD: The approach uses a two-stage pipeline, combining a dictionary-based entity recognizer with a machine-learning classifier. First, the OGER entity recognizer, which has a bias towards high recall, annotates the terms that appear in selected domain ontologies. Subsequently, the Distiller framework uses this information as a feature for a machine learning algorithm to select the relevant entities only. For this step, we compare two different supervised machine-learning algorithms: Conditional Random Fields and Neural Networks. RESULTS: In an in-domain evaluation using the CRAFT corpus, we test the performance of the combined systems when recognizing chemicals, cell types, cellular components, biological processes, molecular functions, organisms, proteins, and biological sequences. Our best system combines dictionary-based candidate generation with Neural-Network-based filtering. It achieves an overall precision of 86% at a recall of 60% on the named entity recognition task, and a precision of 51% at a recall of 49% on the concept recognition task. CONCLUSION: These results are to our knowledge the best reported so far in this particular task.