We present a system for automatically detecting and classifying phonologically anomalous productions in the speech of individuals with aphasia. Working from transcribed discourse samples, our system identifies neologisms, and uses a combination of string alignment and language models to produce a lattice of plausible words that the speaker may have intended to produce. We then score this lattice according to various features, and attempt to determine whether the anomalous production represented a phonemic error or a genuine neologism. This approach has the potential to be expanded to consider other types of paraphasic errors, and could be applied to a wide variety of screening and therapeutic applications.

We propose a novel attention mechanism for a Convolutional Neural Network (CNN)-based Drug-Drug Interaction (DDI) extraction model. CNNs have been shown to have a great potential on DDI extraction tasks; however, attention mechanisms, which emphasize important words in the sentence of a target-entity pair, have not been investigated with the CNNs despite the fact that attention mechanisms are shown to be effective for a general domain relation classification task. We evaluated our model on the Task 9.2 of the DDIExtraction-2013 shared task. As a result, our attention mechanism improved the performance of our base CNN-based DDI model, and the model achieved an F-score of 69.12%, which is competitive with the state-of-the-art models.

Analogy completion has been a popular task in recent years for evaluating the semantic properties of word embeddings, but the standard methodology makes a number of assumptions about analogies that do not always hold, either in recent benchmark datasets or when expanding into other domains. Through an analysis of analogies in the biomedical domain, we identify three assumptions: that of a Single Answer for any given analogy, that the pairs involved describe the Same Relationship, and that each pair is Informative with respect to the other. We propose modifying the standard methodology to relax these assumptions by allowing for multiple correct answers, reporting MAP and MRR in addition to accuracy, and using multiple example pairs. We further present BMASS, a novel dataset for evaluating linguistic regularities in biomedical embeddings, and demonstrate that the relationships described in the dataset pose significant semantic challenges to current word embedding methods.

State-of-the-art methods for protein-protein interaction (PPI) extraction are primarily feature-based or kernel-based by leveraging lexical and syntactic information. But how to incorporate such knowledge in the recent deep learning methods remains an open question. In this paper, we propose a multichannel dependency-based convolutional neural network model (McDepCNN). It applies one channel to the embedding vector of each word in the sentence, and another channel to the embedding vector of the head of the corresponding word. Therefore, the model can use richer information obtained from different channels. Experiments on two public benchmarking datasets, AIMed and BioInfer, demonstrate that McDepCNN provides up to 6% F1-score improvement over rich feature-based methods and single-kernel methods. In addition, McDepCNN achieves 24.4% relative improvement in F1-score over the state-of-the-art methods on cross-corpus evaluation and 12% improvement in F1-score over kernel-based methods on “difficult” instances. These results suggest that McDepCNN generalizes more easily over different corpora, and is capable of capturing long distance features in the sentences.

Linking spans of natural language text to concepts in a structured source is an important task for many problems. It allows intelligent systems to leverage rich knowledge available in those sources (such as concept properties and relations) to enhance the semantics of the mentions of these concepts in text. In the medical domain, it is common to link text spans to medical concepts in large, curated knowledge repositories such as the Unified Medical Language System. Different approaches have different strengths: some are precision-oriented, some recall-oriented; some better at considering context but more prone to hallucination. The variety of techniques suggests that ensembling could outperform component technologies at this task. In this paper, we describe our process for building a Stacking ensemble using additional, auxiliary features for Entity Linking in the medical domain. We report experiments that show that naive ensembling does not always outperform component Entity Linking systems, that stacking usually outperforms naive ensembling, and that auxiliary features added to the stacker further improve its performance on three distinct datasets. Our best model produces state-of-the-art results on several medical datasets.

The goal of the BioASQ challenge is to engage researchers into creating cuttingedge biomedical information systems. Specifically, it aims at the promotion of systems and methodologies that are able to deal with a plethora of different tasks in the biomedical domain. This is achieved through the organization of challenges. The fifth challenge consisted of three tasks: semantic indexing, question answering and a new task on information extraction. In total, 29 teams with more than 95 systems participated in the challenge. Overall, as in previous years, the best systems were able to outperform the strong baselines. This suggests that state-of-the art systems are continuously improving, pushing the frontier of research.

In this paper, we describe our participation in phase B of task 5b of the fifth edition of the annual BioASQ challenge, which includes answering factoid, list, yes-no and summary questions from biomedical data. We describe our techniques with an emphasis on ideal answer generation, where the goal is to produce a relevant, precise, non-redundant, query-oriented summary from multiple relevant documents. We make use of extractive summarization techniques to address this task and experiment with different biomedical ontologies and various algorithms including agglomerative clustering, Maximum Marginal Relevance (MMR) and sentence compression. We propose a novel word embedding based tf-idf similarity metric and a soft positional constraint which improve our system performance. We evaluate our techniques on test batch 4 from the fourth edition of the challenge. Our best system achieves a ROUGE-2 score of 0.6534 and ROUGE-SU4 score of 0.6536.

Macquarie University’s contribution to the BioASQ challenge (Task 5b Phase B) focused on the use of query-based extractive summarisation techniques for the generation of the ideal answers. Four runs were submitted, with approaches ranging from a trivial system that selected the first n snippets, to the use of deep learning approaches under a regression framework. Our experiments and the ROUGE results of the five test batches of BioASQ indicate surprisingly good results for the trivial approach. Overall, most of our runs on the first three test batches achieved the best ROUGE-SU4 results in the challenge.

This paper describes our submission to the 2017 BioASQ challenge. We participated in Task B, Phase B which is concerned with biomedical question answering (QA). We focus on factoid and list question, using an extractive QA model, that is, we restrict our system to output substrings of the provided text snippets. At the core of our system, we use FastQA, a state-of-the-art neural QA system. We extended it with biomedical word embeddings and changed its answer layer to be able to answer list questions in addition to factoid questions. We pre-trained the model on a large-scale open-domain QA dataset, SQuAD, and then fine-tuned the parameters on the BioASQ training set. With our approach, we achieve state-of-the-art results on factoid questions and competitive results on list questions.

We introduce an end-to-end system capable of named-entity detection, normalization and relation extraction for extracting information about bacteria and their habitats from biomedical literature. Our system is based on deep learning, CRF classifiers and vector space models. We train and evaluate the system on the BioNLP 2016 Shared Task Bacteria Biotope data. The official evaluation shows that the joint performance of our entity detection and relation extraction models outperforms the winning team of the Shared Task by 19pp on F1-score, establishing a new top score for the task. We also achieve state-of-the-art results in the normalization task. Our system is open source and freely available at https://github.com/TurkuNLP/BHE.

ext mining automatically extracts information from the literature with the goal of making it available for further analysis, for example by incorporating it into biomedical databases. A key first step towards this goal is to identify and normalize the named entities, such as proteins and species, which are mentioned in text. Despite the large detrimental impact that viruses have on human and agricultural health, very little previous text-mining work has focused on identifying virus species and proteins in the literature. Here, we present an improved dictionary-based system for viral species and the first dictionary for viral proteins, which we benchmark on a new corpus of 300 manually annotated abstracts. We achieve 81.0% precision and 72.7% recall at the task of recognizing and normalizing viral species and 76.2% precision and 34.9% recall on viral proteins. These results are achieved despite the many challenges involved with the names of viral species and, especially, proteins. This work provides a foundation that can be used to extract more complicated relations about viruses from the literature.

We propose in this paper a semi-supervised method for labeling terms of texts with concepts of a domain ontology. The method generates continuous vector representations of complex terms in a semantic space structured by the ontology. The proposed method relies on a distributional semantics approach, which generates initial vectors for each of the extracted terms. Then these vectors are embedded in the vector space constructed from the structure of the ontology. This embedding is carried out by training a linear model. Finally, we apply a distance calculation to determine the proximity between vectors of terms and vectors of concepts and thus to assign ontology labels to terms. We have evaluated the quality of these representations for a normalization task by using the concepts of an ontology as semantic labels. Normalization of terms is an important step to extract a part of the information containing in texts, but the vector space generated might find other applications. The performance of this method is comparable to that of the state of the art for this task of standardization, opening up encouraging prospects.

Vector space methods that measure semantic similarity and relatedness often rely on distributional information such as co–occurrence frequencies or statistical measures of association to weight the importance of particular co–occurrences. In this paper, we extend these methods by incorporating a measure of semantic similarity based on a human curated taxonomy into a second–order vector representation. This results in a measure of semantic relatedness that combines both the contextual information available in a corpus–based vector space representation with the semantic knowledge found in a biomedical ontology. Our results show that incorporating semantic similarity into a second order co-occurrence matrices improves correlation with human judgments for both similarity and relatedness, and that our method compares favorably to various different word embedding methods that have recently been evaluated on the same reference standards we have used.

The goal of active learning is to minimise the cost of producing an annotated dataset, in which annotators are assumed to be perfect, i.e., they always choose the correct labels. However, in practice, annotators are not infallible, and they are likely to assign incorrect labels to some instances. Proactive learning is a generalisation of active learning that can model different kinds of annotators. Although proactive learning has been applied to certain labelling tasks, such as text classification, there is little work on its application to named entity (NE) tagging. In this paper, we propose a proactive learning method for producing NE annotated corpora, using two annotators with different levels of expertise, and who charge different amounts based on their levels of experience. To optimise both cost and annotation quality, we also propose a mechanism to present multiple sentences to annotators at each iteration. Experimental results for several corpora show that our method facilitates the construction of high-quality NE labelled datasets at minimal cost.

We propose a novel, Abstract Meaning Representation (AMR) based approach to identifying molecular events/interactions in biomedical text. Our key contributions are: (1) an empirical validation of our hypothesis that an event is a subgraph of the AMR graph, (2) a neural network-based model that identifies such an event subgraph given an AMR, and (3) a distant supervision based approach to gather additional training data. We evaluate our approach on the 2013 Genia Event Extraction dataset and show promising results.

Social media sites (e.g., Twitter) have been used for surveillance of drug safety at the population level, but studies that focus on the effects of medications on specific sets of individuals have had to rely on other sources of data. Mining social media data for this in-formation would require the ability to distinguish indications of personal medication in-take in this media. Towards that end, this paper presents an annotated corpus that can be used to train machine learning systems to determine whether a tweet that mentions a medication indicates that the individual posting has taken that medication at a specific time. To demonstrate the utility of the corpus as a training set, we present baseline results of supervised classification.

We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. We greatly outperform two baseline off-the-shelf spelling correction tools on a manually annotated MIMIC-III test set, and counter the frequency bias of an optimized noisy channel model, showing that neural embeddings can be successfully exploited to include context-awareness in a spelling correction model.

Approximately 80% to 95% of patients with Amyotrophic Lateral Sclerosis (ALS) eventually develop speech impairments, such as defective articulation, slow laborious speech and hypernasality. The relationship between impaired speech and asymptomatic speech may be seen as a divergence from a baseline. This relationship can be characterized in terms of measurable combinations of phonological characteristics that are indicative of the degree to which the two diverge. We demonstrate that divergence measurements based on phonological characteristics of speech correlate with physiological assessments of ALS. Speech-based assessments offer benefits over commonly-used physiological assessments in that they are inexpensive, non-intrusive, and do not require trained clinical personnel for administering and interpreting the results.

In clinical dictation, speakers try to be as concise as possible to save time, often resulting in utterances without explicit punctuation commands. Since the end product of a dictated report, e.g. an out-patient letter, does require correct orthography, including exact punctuation, the latter need to be restored, preferably by automated means. This paper describes a method for punctuation restoration based on a state-of-the-art stack of NLP and machine learning techniques including B-RNNs with an attention mechanism and late fusion, as well as a feature extraction technique tailored to the processing of medical terminology using a novel vocabulary reduction model. To the best of our knowledge, the resulting performance is superior to that reported in prior art on similar tasks.

Detecting negated concepts in clinical texts is an important part of NLP information extraction systems. However, generalizability of negation systems is lacking, as cross-domain experiments suffer dramatic performance losses. We examine the performance of multiple unsupervised domain adaptation algorithms on clinical negation detection, finding only modest gains that fall well short of in-domain performance.

The Precision Medicine Track in BioCre-ative VI aims to bring together the Bi-oNLP community for a novel challenge focused on mining the biomedical litera-ture in search of mutations and protein-protein interactions (PPI). In order to support this track with an effective train-ing dataset with limited curator time, the track organizers carefully reviewed Pub-Med articles from two different sources: curated public PPI databases, and the re-sults of state-of-the-art public text mining tools. We detail here the data collection, manual review and annotation process and describe this training corpus charac-teristics. We also describe a corpus per-formance baseline. This analysis will provide useful information to developers and researchers for comparing and devel-oping innovative text mining approaches for the BioCreative VI challenge and other Precision Medicine related applica-tions.

Relation extraction methods are essential for creating robust text mining tools to help researchers find useful knowledge in the vast published literature. Easy-to-use and generalizable methods are needed to encourage an ecosystem in which researchers can easily use shared resources and build upon each others’ methods. We present the Kindred Python package for relation extraction. It builds upon methods from the most successful tools in the recent BioNLP Shared Task to predict high-quality predictions with low computational cost. It also integrates with PubAnnotation, PubTator, and BioNLP Shared Task data in order to allow easy development and application of relation extraction models.

Distant supervision has been applied to automatically generate labeled data for biomedical relation extraction. Noise exists in both positively and negatively-labeled data and affects the performance of supervised machine learning methods. In this paper, we propose three novel heuristics based on the notion of proximity, trigger word and confidence of patterns to leverage lexical and syntactic information to reduce the level of noise in the distantly labeled data. Experiments on three different tasks, extraction of protein-protein-interaction, miRNA-gene regulation relation and protein-localization event, show that the proposed methods can improve the F-score over the baseline by 6, 10 and 14 points for the three tasks, respectively. We also show that when the models are configured to output high-confidence results, high precisions can be obtained using the proposed methods, making them promising for facilitating manual curation for databases.

Electronic medical records (EMR) have largely replaced hand-written patient files in healthcare. The growing pool of EMR data presents a significant resource in medical research, but the U.S. Health Insurance Portability and Accountability Act (HIPAA) mandates redacting medical records before performing any analysis on the same. This process complicates obtaining medical data and can remove much useful information from the record. As part of a larger project involving ontology-driven medical processing, we employ a method of recognizing protected health information (PHI) that maps to ontological terms. We then use the relationships defined in the ontology to redact medical texts so that roles and semantics of terms are retained without compromising anonymity. The method is evaluated by clinical experts on several hundred medical documents, achieving up to a 98.8% f-score, and has already shown promise for retaining semantic information in later processing.

Pain and anesthesia information are crucial elements to identifying surgery-related processes and outcomes. However pain is not consistently recorded in the electronic medical record. Even when recorded, the rich complex granularity of the pain experience may be lost. Similarly, anesthesia information is recorded using local electronic collection systems; though the accuracy and completeness of the information is unknown. We propose an annotation schema to capture pain, pain management, and anesthesia event information.

Comparison sentences are very commonly used by authors in biomedical literature to report results of experiments. In such comparisons, authors typically make observations under two different scenarios. In this paper, we present a system to automatically identify such comparative sentences and their components i.e. the compared entities, the scale of the comparison and the aspect on which the entities are being compared. Our methodology is based on dependencies obtained by applying a parser to extract a wide range of comparison structures. We evaluated our system for its effectiveness in identifying comparisons and their components. The system achieved a F-score of 0.87 for comparison sentence identification and 0.77-0.81 for identifying its components.

In this paper we present a solution for tagging funding bodies and grants in scientific articles using a combination of trained sequential learning models, namely conditional random fields (CRF), hidden markov models (HMM) and maximum entropy models (MaxEnt), on a benchmark set created in-house. We apply the trained models to address the BioASQ challenge 5c, which is a newly introduced task that aims to solve the problem of funding information extraction from scientific articles. Results in the dry-run data set of BioASQ task 5c show that the suggested approach can achieve a micro-recall of more than 85% in tagging both funding bodies and grants.

We describe a Deep Learning approach to modeling the relevance of a document’s text to a query, applied to biomedical literature. Instead of mapping each document and query to a common semantic space, we compute a variable-length difference vector between the query and document which is then passed through a deep convolution stage followed by a deep regression network to produce the estimated probability of the document’s relevance to the query. Despite the small amount of training data, this approach produces a more robust predictor than computing similarities between semantic vector representations of the query and document, and also results in significant improvements over traditional IR text factors. In the future, we plan to explore its application in improving PubMed search.

We investigate if writers with dementia can be automatically distinguished from those without by analyzing linguistic markers in written text, in the form of blog posts. We have built a corpus of several thousand blog posts, some by people with dementia and others by people with loved ones with dementia. We use this dataset to train and test several machine learning methods, and achieve prediction performance at a level far above the baseline.

Literature in Molecular Biology is abundant with linguistic metaphors. There have been works in the past that attempt to draw parallels between linguistics and biology, driven by the fundamental premise that proteins have a language of their own. Since word detection is crucial to the decipherment of any unknown language, we attempt to establish a problem mapping from natural language text to protein sequences at the level of words. Towards this end, we explore the use of an unsupervised text segmentation algorithm to the task of extracting “biological words” from protein sequences. In particular, we demonstrate the effectiveness of using domain knowledge to complement data driven approaches in the text segmentation task, as well as in its biological counterpart. We also propose a novel extrinsic evaluation measure for protein words through protein family classification.

This paper evaluates the impact of various event extraction systems on automatic pathway curation using the popular mTOR pathway. We quantify the impact of training data sets as well as different machine learning classifiers and show that some improve the quality of automatically extracted pathways.

Severe sepsis and septic shock are conditions that affect millions of patients and have close to 50% mortality rate. Early identification of at-risk patients significantly improves outcomes. Electronic surveillance tools have been developed to monitor structured Electronic Medical Records and automatically recognize early signs of sepsis. However, many sepsis risk factors (e.g. symptoms and signs of infection) are often captured only in free text clinical notes. In this study, we developed a method for automatic monitoring of nursing notes for signs and symptoms of infection. We utilized a creative approach to automatically generate an annotated dataset. The dataset was used to create a Machine Learning model that achieved an F1-score ranging from 79 to 96%.

Assigning a standard ICD-9-CM code to disease symptoms in medical texts is an important task in the medical domain. Automating this process could greatly reduce the costs. However, the effectiveness of an automatic ICD-9-CM code classifier faces a serious problem, which can be triggered by unbalanced training data. Frequent diseases often have more training data, which helps its classification to perform better than that of an infrequent disease. However, a disease’s frequency does not necessarily reflect its importance. To resolve this training data shortage problem, we propose to strategically draw data from PubMed to enrich the training data when there is such need. We validate our method on the CMC dataset, and the evaluation results indicate that our method can significantly improve the code assignment classifiers’ performance at the macro-averaging level.

In this paper, we present an analysis of feature extraction methods via dimensionality reduction for the task of biomedical Word Sense Disambiguation (WSD). We modify the vector representations in the 2-MRD WSD algorithm, and evaluate four dimensionality reduction methods: Word Embeddings using Continuous Bag of Words and Skip Gram, Singular Value Decomposition (SVD), and Principal Component Analysis (PCA). We also evaluate the effects of vector size on the performance of each of these methods. Results are evaluated on five standard evaluation datasets (Abbrev.100, Abbrev.200, Abbrev.300, NLM-WSD, and MSH-WSD). We find that vector sizes of 100 are sufficient for all techniques except SVD, for which a vector size of 1500 is referred. We also show that SVD performs on par with Word Embeddings for all but one dataset.

In this paper, we present pilot work on characterising the documentation of electronic cigarettes (e-cigarettes) in the United States Veterans Administration Electronic Health Record. The Veterans Health Administration is the largest health care system in the United States with 1,233 health care facilities nationwide, serving 8.9 million veterans per year. We identified a random sample of 2000 Veterans Administration patients, coded as current tobacco users, from 2008 to 2014. Using simple keyword matching techniques combined with qualitative analysis, we investigated the prevalence and distribution of e-cigarette terms in these clinical notes, discovering that for current smokers, 11.9% of patient records contain an e-cigarette related term.

Dictated medical reports very often feature a preamble containing metainformation about the report such as patient and physician names, location and name of the clinic, date of procedure, and so on. In the medical transcription process, the preamble is usually omitted from the final report, as it contains information already available in the electronic medical record. We present a method which is able to automatically identify preambles in medical dictations. The method makes use of state-of-the-art NLP techniques including word embeddings and Bi-LSTMs and achieves preamble detection performance superior to humans.

Question answering, the identification of short accurate answers to users questions, is a longstanding challenge widely studied over the last decades in the open domain. However, it still requires further efforts in the biomedical domain. In this paper, we describe our participation in phase B of task 5b in the 2017 BioASQ challenge using our biomedical question answering system. Our system, dealing with four types of questions (i.e., yes/no, factoid, list, and summary), is based on (1) a dictionary-based approach for generating the exact answers of yes/no questions, (2) UMLS metathesaurus and term frequency metric for extracting the exact answers of factoid and list questions, and (3) the BM25 model and UMLS concepts for retrieving the ideal answers (i.e., paragraph-sized summaries). Preliminary results show that our system achieves good and competitive results in both exact and ideal answers extraction tasks as compared with the participating systems.

Word embeddings are a crucial component in modern NLP. Pre-trained embeddings released by different groups have been a major reason for their popularity. However, they are trained on generic corpora, which limits their direct use for domain specific tasks. In this paper, we propose a method to add task specific information to pre-trained word embeddings. Such information can improve their utility. We add information from medical coding data, as well as the first level from the hierarchy of ICD-10 medical code set to different pre-trained word embeddings. We adapt CBOW algorithm from the word2vec package for our purpose. We evaluated our approach on five different pre-trained word embeddings. Both the original word embeddings, and their modified versions (the ones with added information) were used for automated review of medical coding. The modified word embeddings give an improvement in f-score by 1% on the 5-fold evaluation on a private medical claims dataset. Our results show that adding extra information is possible and beneficial for the task at hand.

Many tasks in the biomedical domain require the assignment of one or more predefined labels to input text, where the labels are a part of a hierarchical structure (such as a taxonomy). The conventional approach is to use a one-vs.-rest (OVR) classification setup, where a binary classifier is trained for each label in the taxonomy or ontology where all instances not belonging to the class are considered negative examples. The main drawbacks to this approach are that dependencies between classes are not leveraged in the training and classification process, and the additional computational cost of training parallel classifiers. In this paper, we apply a new method for hierarchical multi-label text classification that initializes a neural network model final hidden layer such that it leverages label co-occurrence relations such as hypernymy. This approach elegantly lends itself to hierarchical classification. We evaluated this approach using two hierarchical multi-label text classification tasks in the biomedical domain using both sentence- and document-level classification. Our evaluation shows promising results for this approach.

Biomedical events describe complex interactions between various biomedical entities. Event trigger is a word or a phrase which typically signifies the occurrence of an event. Event trigger identification is an important first step in all event extraction methods. However many of the current approaches either rely on complex hand-crafted features or consider features only within a window. In this paper we propose a method that takes the advantage of recurrent neural network (RNN) to extract higher level features present across the sentence. Thus hidden state representation of RNN along with word and entity type embedding as features avoid relying on the complex hand-crafted features generated using various NLP toolkits. Our experiments have shown to achieve state-of-art F1-score on Multi Level Event Extraction (MLEE) corpus. We have also performed category-wise analysis of the result and discussed the importance of various features in trigger identification task.

Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task.

Diagnosis autocoding services and research intend to both improve the productivity of clinical coders and the accuracy of the coding. It is an important step in data analysis for funding and reimbursement, as well as health services planning and resource allocation. We investigate the applicability of deep learning at autocoding of radiology reports using International Classification of Diseases (ICD). Deep learning methods are known to require large training data. Our goal is to explore how to use these methods when the training data is sparse, skewed and relatively small, and how their effectiveness compares to conventional methods. We identify optimal parameters that could be used in setting up a convolutional neural network for autocoding with comparable results to that of conventional methods.

We present the work-in-progress of automating the classification of doctor-patient questions in the context of a simulated consultation with a virtual patient. We classify questions according to the computational strategy (rule-based or other) needed for looking up data in the clinical record. We compare ‘traditional’ machine learning methods (Gaussian and Multinomial Naive Bayes, and Support Vector Machines) and a neural network classifier (FastText). We obtained the best results with the SVM using semantic annotations, whereas the neural classifier achieved promising results without it.

Question answering (QA) can support physicians and biomedical researchers to find answers to their questions in the scientific literature. Such systems process large collections of documents in real time and include many natural language processing (NLP) procedures. We recently developed Olelo, a QA system for biomedicine which includes various NLP components, such as question processing, document and passage retrieval, answer processing and multi-document summarization. In this work, we present an evaluation of our system on the the fifth BioASQ challenge. We participated with the current state of the application and with an extension based on semantic role labeling that we are currently investigating. In addition to the BioASQ evaluation, we compared our system to other on-line biomedical QA systems in terms of the response time and the quality of the answers.

Event detection from clinical notes has been traditionally solved with rule based and statistical natural language processing (NLP) approaches that require extensive domain knowledge and feature engineering. In this paper, we have explored the feasibility of approaching this task with recurrent neural networks, clinical word embeddings and introduced a hybrid architecture to improve detection for entities with smaller representation in the dataset. A comparative analysis is also done which reveals the complementary behavior of neural networks and conditional random fields in clinical entity detection.

In this paper, we describe a system for automatic construction of user disease progression timelines from their posts in online support groups using minimal supervision. In recent years, several online support groups have been established which has led to a huge increase in the amount of patient-authored text available. Creating systems which can automatically extract important medical events and create disease progression timelines for users from such text can help in patient health monitoring as well as studying links between medical events and users’ participation in support groups. Prior work in this domain has used manually constructed keyword sets to detect medical events. In this work, our aim is to perform medical event detection using minimal supervision in order to develop a more general timeline construction system. Our system achieves an accuracy of 55.17%, which is 92% of the performance achieved by a supervised baseline system.

We study and compare two different approaches to the task of automatic assignment of predefined classes to clinical free-text narratives. In the first approach this is treated as a traditional mention-level named-entity recognition task, while the second approach treats it as a sentence-level multi-label classification task. Performance comparison across these two approaches is conducted in the form of sentence-level evaluation and state-of-the-art methods for both approaches are evaluated. The experiments are done on two data sets consisting of Finnish clinical text, manually annotated with respect to the topics pain and acute confusion. Our results suggest that the mention-level named-entity recognition approach outperforms sentence-level classification overall, but the latter approach still manages to achieve the best prediction scores on several annotation classes.

This paper describes the participation of USTB_PRIR team in the 2017 BioASQ 5B on question answering, including document retrieval, snippet retrieval, and concept retrieval task. We introduce different multimodal query processing strategies to enrich query terms and assign different weights to them. Specifically, sequential dependence model (SDM), pseudo-relevance feedback (PRF), fielded sequential dependence model (FSDM) and Divergence from Randomness model (DFRM) are respectively performed on different fields of PubMed articles, sentences extracted from relevant articles, the five terminologies or ontologies (MeSH, GO, Jochem, Uniprot and DO) to achieve better search performances. Preliminary results show that our systems outperform others in the document and snippet retrieval task in the first two batches.