Dataset Information

Automatic query generation using word embeddings for retrieving passages describing experimental methods.

ABSTRACT: Information regarding the physical interactions among proteins is crucial, since protein-protein interactions (PPIs) are central for many biological processes. The experimental techniques used to verify PPIs are vital for characterizing and assessing the reliability of the identified PPIs. A lot of information about PPIs and the experimental methods are only available in the text of the scientific publications that report them. In this study, we approach the problem of identifying passages with experimental methods for physical interactions between proteins as an information retrieval search task. The baseline system is based on query matching, where the queries are generated by utilizing the names (including synonyms) of the experimental methods in the Proteomics Standard Initiative-Molecular Interactions (PSI-MI) ontology. We propose two methods, where the baseline queries are expanded by including additional relevant terms. The first method is a supervised approach, where the most salient terms for each experimental method are obtained by using the term frequency-relevance frequency (tf.rf) metric over 13 articles from our manually annotated data set of 30 full text articles, which is made publicly available. On the other hand, the second method is an unsupervised approach, where the queries for each experimental method are expanded by using the word embeddings of the names of the experimental methods in the PSI-MI ontology. The word embeddings are obtained by utilizing a large unlabeled full text corpus. The proposed methods are evaluated on the test set consisting of 17 articles. Both methods obtain higher recall scores compared with the baseline, with a loss in precision. Besides higher recall, the word embeddings based approach achieves higher F-measure than the baseline and the tf.rf based methods. We also show that incorporating gene name and interaction keyword identification leads to improved precision and F-measure scores for all three evaluated methods. The tf.rf based approach was developed as part of our participation in the Collaborative Biocurator Assistant Task of the BioCreative V challenge assessment, whereas the word embeddings based approach is a novel contribution of this article.Database URL: https://github.com/ferhtaydn/biocemid/.

SUBMITTER: Ayd?n F

PROVIDER: S-EPMC5225401 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic query generation using word embeddings for retrieving passages describing experimental methods.

Aydın Ferhat F Hüsünbeyi Zehra Melce ZM Özgür Arzucan A

Database : the journal of biological databases and curation 20170110

Information regarding the physical interactions among proteins is crucial, since protein-protein interactions (PPIs) are central for many biological processes. The experimental techniques used to verify PPIs are vital for characterizing and assessing the reliability of the identified PPIs. A lot of information about PPIs and the experimental methods are only available in the text of the scientific publications that report them. In this study, we approach the problem of identifying passages with ...[more]

PMID: 28077568

Similar Datasets

Project description:BackgroundThere has been increasing interest in machine learning based natural language processing (NLP) methods in radiology; however, models have often used word embeddings trained on general web corpora due to lack of a radiology-specific corpus.PurposeWe examined the potential of Radiopaedia to serve as a general radiology corpus to produce radiology specific word embeddings that could be used to enhance performance on a NLP task on radiological text.Materials and methodsEmbeddings of dimension 50, 100, 200, and 300 were trained on articles collected from Radiopaedia using a GloVe algorithm and evaluated on analogy completion. A shallow neural network using input from either our trained embeddings or pre-trained Wikipedia 2014 + Gigaword 5 (WG) embeddings was used to label the Radiopaedia articles. Labeling performance was evaluated based on exact match accuracy and Hamming loss. The McNemar's test with continuity and the Benjamini-Hochberg correction and a 5×2 cross validation paired two-tailed t-test were used to assess statistical significance.ResultsFor accuracy in the analogy task, 50-dimensional (50-D) Radiopaedia embeddings outperformed WG embeddings on tumor origin analogies (p < 0.05) and organ adjectives (p < 0.01) whereas WG embeddings tended to outperform on inflammation location and bone vs. muscle analogies (p < 0.01). The two embeddings had comparable performance on other subcategories. In the labeling task, the Radiopaedia-based model outperformed the WG based model at 50, 100, 200, and 300-D for exact match accuracy (p < 0.001, p < 0.001, p < 0.01, and p < 0.05, respectively) and Hamming loss (p < 0.001, p < 0.001, p < 0.01, and p < 0.05, respectively).ConclusionWe have developed a set of word embeddings from Radiopaedia and shown that they can preserve relevant medical semantics and augment performance on a radiology NLP task. Our results suggest that the cultivation of a radiology-specific corpus can benefit radiology NLP models in the future.

Project description:BackgroundWord embeddings have been prevalently used in biomedical Natural Language Processing (NLP) applications due to the ability of the vector representations being able to capture useful semantic properties and linguistic relationships between words. Different textual resources (e.g., Wikipedia and biomedical literature corpus) have been utilized in biomedical NLP to train word embeddings and these word embeddings have been commonly leveraged as feature input to downstream machine learning models. However, there has been little work on evaluating the word embeddings trained from different textual resources.MethodsIn this study, we empirically evaluated word embeddings trained from four different corpora, namely clinical notes, biomedical publications, Wikipedia, and news. For the former two resources, we trained word embeddings using unstructured electronic health record (EHR) data available at Mayo Clinic and articles (MedLit) from PubMed Central, respectively. For the latter two resources, we used publicly available pre-trained word embeddings, GloVe and Google News. The evaluation was done qualitatively and quantitatively. For the qualitative evaluation, we randomly selected medical terms from three categories (i.e., disorder, symptom, and drug), and manually inspected the five most similar words computed by embeddings for each term. We also analyzed the word embeddings through a 2-dimensional visualization plot of 377 medical terms. For the quantitative evaluation, we conducted both intrinsic and extrinsic evaluation. For the intrinsic evaluation, we evaluated the word embeddings' ability to capture medical semantics by measruing the semantic similarity between medical terms using four published datasets: Pedersen's dataset, Hliaoutakis's dataset, MayoSRS, and UMNSRS. For the extrinsic evaluation, we applied word embeddings to multiple downstream biomedical NLP applications, including clinical information extraction (IE), biomedical information retrieval (IR), and relation extraction (RE), with data from shared tasks.ResultsThe qualitative evaluation shows that the word embeddings trained from EHR and MedLit can find more similar medical terms than those trained from GloVe and Google News. The intrinsic quantitative evaluation verifies that the semantic similarity captured by the word embeddings trained from EHR is closer to human experts' judgments on all four tested datasets. The extrinsic quantitative evaluation shows that the word embeddings trained on EHR achieved the best F1 score of 0.900 for the clinical IE task; no word embeddings improved the performance for the biomedical IR task; and the word embeddings trained on Google News had the best overall F1 score of 0.790 for the RE task.ConclusionBased on the evaluation results, we can draw the following conclusions. First, the word embeddings trained from EHR and MedLit can capture the semantics of medical terms better, and find semantically relevant medical terms closer to human experts' judgments than those trained from GloVe and Google News. Second, there does not exist a consistent global ranking of word embeddings for all downstream biomedical NLP applications. However, adding word embeddings as extra features will improve results on most downstream tasks. Finally, the word embeddings trained from the biomedical domain corpora do not necessarily have better performance than those trained from the general domain corpora for any downstream biomedical NLP task.

Project description:Increased interest in the use of word embeddings, such as word representation, for biomedical named entity recognition (BioNER) has highlighted the need for evaluations that aid in selecting the best word embedding to be used. One common criterion for selecting a word embedding is the type of source from which it is generated; that is, general (e.g., Wikipedia, Common Crawl), or specific (e.g., biomedical literature). Using specific word embeddings for the BioNER task has been strongly recommended, considering that they have provided better coverage and semantic relationships among medical entities. To the best of our knowledge, most studies have focused on improving BioNER task performance by, on the one hand, combining several features extracted from the text (for instance, linguistic, morphological, character embedding, and word embedding itself) and, on the other, testing several state-of-the-art named entity recognition algorithms. The latter, however, do not pay great attention to the influence of the word embeddings, and do not facilitate observing their real impact on the BioNER task. For this reason, the present study evaluates three well-known NER algorithms (CRF, BiLSTM, BiLSTM-CRF) with respect to two corpora (DrugBank and MedLine) using two classic word embeddings, GloVe Common Crawl (of the general type) and Pyysalo PM + PMC (specific), as unique features. Furthermore, three contextualized word embeddings (ELMo, Pooled Flair, and Transformer) are compared in their general and specific versions. The aim is to determine whether general embeddings can perform better than specialized ones on the BioNER task. To this end, four experiments were designed. In the first, we set out to identify the combination of classic word embedding, NER algorithm, and corpus that results in the best performance. The second evaluated the effect of the size of the corpus on performance. The third assessed the semantic cohesiveness of the classic word embeddings and their correlation with respect to several gold standards; while the fourth evaluates the performance of general and specific contextualized word embeddings on the BioNER task. Results show that the classic general word embedding GloVe Common Crawl performed better in the DrugBank corpus, despite having less word coverage and a lower internal semantic relationship than the classic specific word embedding, Pyysalo PM + PMC; while in the contextualized word embeddings the best results are presented in the specific ones. We conclude, therefore, when using classic word embeddings as features on the BioNER task, the general ones could be considered a good option. On the other hand, when using contextualized word embeddings, the specific ones are the best option.

Dataset Information

Automatic query generation using word embeddings for retrieving passages describing experimental methods.

Publications

Automatic query generation using word embeddings for retrieving passages describing experimental methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure