Learning about phraseology from corpora: A linguistically motivated approach for Multiword Expression identification.
Ontology highlight
ABSTRACT:
SUBMITTER: Inurrieta U
PROVIDER: S-EPMC7451662 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Learning about phraseology from corpora: A linguistically motivated approach for Multiword Expression identification.
Inurrieta Uxoa U Aduriz Itziar I Díaz de Ilarraza Arantza A Labaka Gorka G Sarasola Kepa K
PloS one 20200827 8
Multiword Expressions (MWEs) are idiosyncratic combinations of words which pose important challenges to Natural Language Processing. Some kinds of MWEs, such as verbal ones, are particularly hard to identify in corpora, due to their high degree of morphosyntactic flexibility. This paper describes a linguistically motivated method to gather detailed information about verb+noun MWEs (VNMWEs) from corpora. Although the main focus of this study is Spanish, the method is easily adaptable to other lan ...[more]
Similar Datasets
Project description:Identifying the relations among different regions of the brain is vital for a better understanding of how the brain functions. While a large number of studies have investigated the neuroanatomical and neurochemical connections among brain structures, their specific findings are found in publications scattered over a large number of years and different types of publications. Text mining techniques have provided the means to extract specific types of information from a large number of publications with the aim of presenting a larger, if not necessarily an exhaustive picture. By using natural language processing techniques, the present paper aims to identify connectivity relations among brain regions in general and relations relevant to the paraventricular nucleus of the thalamus (PVT) in particular. We introduce a linguistically motivated approach based on patterns defined over the constituency and dependency parse trees of sentences. Besides the presence of a relation between a pair of brain regions, the proposed method also identifies the directionality of the relation, which enables the creation and analysis of a directional brain region connectivity graph. The approach is evaluated over the manually annotated data sets of the WhiteText Project. In addition, as a case study, the method is applied to extract and analyze the connectivity graph of PVT, which is an important brain region that is considered to influence many functions ranging from arousal, motivation, and drug-seeking behavior to attention. The results of the PVT connectivity graph show that PVT may be a new target of research in mood assessment.
| S-EPMC5030238 | biostudies-literature
Project description:BackgroundAphasia therapy focusing on abstract properties of language promotes both item-specific effects and generalization to untreated materials. Neuromodulation with transcranial Direct Current Stimulation (tDCS) has been shown to enhance item-specific improvement, but its potential to enhance generalization has not been systematically investigated. Here, we test the efficacy of ACTION (a linguistically motivated protocol) and tDCS in producing item-specific and generalized improvement in aphasia.MethodNine individuals with post-stroke aphasia participated in this study. Participants were pre-tested with a diagnostic language battery and a cognitive screening. Experimental tasks were administered over multiple baselines. Production of infinitives, of finite verbs and of full sentences were assessed before and after each treatment phase. Nonword repetition was used as a control measure. Each subject was treated in two phases. Ten daily 1-h treatment sessions were provided per phase, in a double-blind, cross-over design. Linguistically-motivated language therapy focusing on verb inflection and sentence construction was provided in both phases. Each session began with 20 min of real or sham tDCS. Stimulation site was determined individually, based on MRI scans.ResultsGroup data showed improved production of treated and untreated verbs, attesting the efficacy of behavioral treatment, and its potential to yield generalization. Each individual showed significant item-specific improvement. Generalization occurred in the first phase of treatment for all subjects, and in the second phase for two subjects. Stimulation effects at the group level were significant for treated and untreated verbs altogether, but a ceiling effect for Sham cannot be excluded, as scores between real tDCS and Sham differed only before treatment.ConclusionOur data demonstrate the efficacy of ACTION and suggest that tDCS may enhance both item-specific effects and generalization.
| S-EPMC4519773 | biostudies-literature
Project description:BACKGROUND: Our goal is to develop a state-of-the-art protein secondary structure predictor, with an intuitive and biophysically-motivated energy model. We treat structure prediction as an optimization problem, using parameterizable cost functions representing biological "pseudo-energies". Machine learning methods are applied to estimate the values of the parameters to correctly predict known protein structures. RESULTS: Focusing on the prediction of alpha helices in proteins, we show that a model with 302 parameters can achieve a Qalpha value of 77.6% and an SOValpha value of 73.4%. Such performance numbers are among the best for techniques that do not rely on external databases (such as multiple sequence alignments). Further, it is easier to extract biological significance from a model with so few parameters. CONCLUSION: The method presented shows promise for the prediction of protein secondary structure. Biophysically-motivated elementary free-energies can be learned using SVM techniques to construct an energy cost function whose predictive performance rivals state-of-the-art. This method is general and can be extended beyond the all-alpha case described here.
| S-EPMC1892091 | biostudies-literature
Project description:ObjectivesTo assess the construct validity and reliability of the motivation section of the Motivated Strategies for Learning Questionnaire in Saudi Arabia.MethodsA cross-sectional study using the Motivated Strategies for Learning Questionnaire (MSLQ) was conducted. The MSQL has essentially two sections: a motivation section and a learning strategies section. The motivation section, which consists of 31 items, was used. A total of 146 medical students who were all male completed the questionnaire. Confirmatory factor analysis was used to test the hypothesised factor structure, and to identify the validity and reliability of the motivation section of the MSQL.ResultsA selected group of fit statistics showed that the hypothesised model did not fit the sample data fairly well. The Intrinsic Goal Orientation subscale consisted of 4 items (? = 0.75), the Extrinsic Goal Orientation subscale consisted of 4 items (? = 0.78), the Task Value subscale consisted of 6 items (? =0.86), the Control of Learning Beliefs consisted of 4 items (? =0.78), the Self-Efficacy for Learning and Performance consisted of 8 items (? =0.89), and the Test Anxiety consisted of 5 items (? =0.77).ConclusionsIt is concluded that the hypothesised model did not fit the data well. This may suggest that the motivation section of the MSQL may not work for Saudi Arabian students. However, this could be due to the fact that the sample data available on this study did not represent female students. Further work is required to establish this. Limitations of the study are discussed.
| S-EPMC6387767 | biostudies-literature
Project description:Past research has found that neural activity associated with feedback processing is enhanced by positive approach-motivated states. However, no past work has examined how reward processing changes in the context of revenge. Using a novel aggression paradigm, we sought to explore the influence of approach-motivated anger on neural responses to feedback indicating the opportunity to seek revenge against an offending opponent by examining the reward positivity (RewP), an event-related potential indexing performance feedback. In Experiment 1, after receiving insulting feedback from an opponent, participants played a reaction time game with three trial types: revenge trials, aggravation trials, and no-consequence trials. Results revealed that RewP amplitudes were larger to revenge trial win feedback than no-consequence trial win feedback or revenge trial loss feedback. RewP amplitudes were larger to both aggravation trial win and loss feedback than on no-consequence trials. Experiment 2 examined the influence of approach-motivated anger during the acquisition of rewards on the RewP without the possibility of retribution from the offending individual. Participants played a reaction time game similar to Experiment 1, except instead of giving or receiving noise blasts, participants could win money from the insulter (revenge trials) or a neutral-party (e.g., bank). Results indicated that revenge wins elicited larger RewP amplitudes than bank wins. These results suggest that anger enhances revenge-related RewP amplitudes to obtaining revenge opportunities and further aggravation wins or losses. Anger appears to enhance the pleasurable feelings of revenge.
| S-EPMC7643382 | biostudies-literature
Project description:CRISPR-Cas are adaptive immune systems that degrade foreign genetic elements in archaea and bacteria. In carrying out their immune functions, CRISPR-Cas systems heavily rely on RNA components. These CRISPR (cr) RNAs are repeat-spacer units that are produced by processing of pre-crRNA, the transcript of CRISPR arrays, and guide Cas protein(s) to the cognate invading nucleic acids, enabling their destruction. Several bioinformatics tools have been developed to detect CRISPR arrays based solely on DNA sequences, but all these tools employ the same strategy of looking for repetitive patterns, which might correspond to CRISPR array repeats. The identified patterns are evaluated using a fixed, built-in scoring function, and arrays exceeding a cut-off value are reported. Here, we instead introduce a data-driven approach that uses machine learning to detect and differentiate true CRISPR arrays from false ones based on several features. Our CRISPR detection tool, CRISPRidentify, performs three steps: detection, feature extraction and classification based on manually curated sets of positive and negative examples of CRISPR arrays. The identified CRISPR arrays are then reported to the user accompanied by detailed annotation. We demonstrate that our approach identifies not only previously detected CRISPR arrays, but also CRISPR array candidates not detected by other tools. Compared to other methods, our tool has a drastically reduced false positive rate. In contrast to the existing tools, our approach not only provides the user with the basic statistics on the identified CRISPR arrays but also produces a certainty score as a practical measure of the likelihood that a given genomic region is a CRISPR array.
| S-EPMC7913763 | biostudies-literature
Project description:Biomedical relation extraction (RE) datasets are vital in the construction of knowledge bases and to potentiate the discovery of new interactions. There are several ways to create biomedical RE datasets, some more reliable than others, such as resorting to domain expert annotations. However, the emerging use of crowdsourcing platforms, such as Amazon Mechanical Turk (MTurk), can potentially reduce the cost of RE dataset construction, even if the same level of quality cannot be guaranteed. There is a lack of power of the researcher to control who, how and in what context workers engage in crowdsourcing platforms. Hence, allying distant supervision with crowdsourcing can be a more reliable alternative. The crowdsourcing workers would be asked only to rectify or discard already existing annotations, which would make the process less dependent on their ability to interpret complex biomedical sentences. In this work, we use a previously created distantly supervised human phenotype-gene relations (PGR) dataset to perform crowdsourcing validation. We divided the original dataset into two annotation tasks: Task 1, 70% of the dataset annotated by one worker, and Task 2, 30% of the dataset annotated by seven workers. Also, for Task 2, we added an extra rater on-site and a domain expert to further assess the crowdsourcing validation quality. Here, we describe a detailed pipeline for RE crowdsourcing validation, creating a new release of the PGR dataset with partial domain expert revision, and assess the quality of the MTurk platform. We applied the new dataset to two state-of-the-art deep learning systems (BiOnt and BioBERT) and compared its performance with the original PGR dataset, as well as combinations between the two, achieving a 0.3494 increase in average F-measure. The code supporting our work and the new release of the PGR dataset is available at https://github.com/lasigeBioTM/PGR-crowd.
| S-EPMC7706181 | biostudies-literature
Project description:Applying machine learning algorithms to automatically infer relationships between concepts from large-scale collections of documents presents a unique opportunity to investigate at scale how human semantic knowledge is organized, how people use it to make fundamental judgments ("How similar are cats and bears?"), and how these judgments depend on the features that describe concepts (e.g., size, furriness). However, efforts to date have exhibited a substantial discrepancy between algorithm predictions and human empirical judgments. Here, we introduce a novel approach to generating embeddings for this purpose motivated by the idea that semantic context plays a critical role in human judgment. We leverage this idea by constraining the topic or domain from which documents used for generating embeddings are drawn (e.g., referring to the natural world vs. transportation apparatus). Specifically, we trained state-of-the-art machine learning algorithms using contextually-constrained text corpora (domain-specific subsets of Wikipedia articles, 50+ million words each) and showed that this procedure greatly improved predictions of empirical similarity judgments and feature ratings of contextually relevant concepts. Furthermore, we describe a novel, computationally tractable method for improving predictions of contextually-unconstrained embedding models based on dimensionality reduction of their internal representation to a small number of contextually relevant semantic features. By improving the correspondence between predictions derived automatically by machine learning methods using vast amounts of data and more limited, but direct empirical measurements of human judgments, our approach may help leverage the availability of online corpora to better understand the structure of human semantic representations and how people make judgments based on those.
| S-EPMC9285590 | biostudies-literature
Project description:This study explored how university students remained motivated to learn, despite all the limitations they encountered and endured during the COVID-19 pandemic. This work was carried out in Indonesia, but the benefits are beyond a state boundary. The study examines how university students in developing countries have faced obstacles, and yet despite this, they are still trying their hardest to stay focused on achieving their personal goals during the pandemic. This research employed a qualitative phenomenological approach, involving eighty students that were studying at the Faculty of Education at a state university in Jakarta, Indonesia. As data collection techniques, students were asked to write learning log diaries and reflective essays and to participate in an online focus group discussion. The results showed that the students' motivation to remain learning during the COVID-19 pandemic fell into three key themes, each with associated sub-themes. The three themes and sub-themes described were: (a) personal, with sub-themes of challenge, curiosity, self-determination, satisfaction and religious commitment; (b) social, with sub-themes of relationships, inspiration, and well-being of self and others; and (c) environmental, with sub-themes of facilities and conditioning. The themes and sub-themes indicate the source of motivation for these university students to learn during the pandemic. This study concluded that these emerging adults were both intrinsically and extrinsically autonomously motivated and committed to their studies. Most of these students were motivated by their consequential aspirations, not by a controlled motivation, nor were they motivated by a reward, a penalty, or a rule that propelled them. By defining how the students managed to empower themselves, this study recommends the importance of preparing students to be more resilient and to enable them to cultivate the ability to remain optimistic and motivated to succeed and overcome any of life's adversities.
| S-EPMC7725050 | biostudies-literature
Project description:Deep neural networks provide the current best models of visual information processing in the primate brain. Drawing on work from computer vision, the most commonly used networks are pretrained on data from the ImageNet Large Scale Visual Recognition Challenge. This dataset comprises images from 1,000 categories, selected to provide a challenging testbed for automated visual object recognition systems. Moving beyond this common practice, we here introduce ecoset, a collection of >1.5 million images from 565 basic-level categories selected to better capture the distribution of objects relevant to humans. Ecoset categories were chosen to be both frequent in linguistic usage and concrete, thereby mirroring important physical objects in the world. We test the effects of training on this ecologically more valid dataset using multiple instances of two neural network architectures: AlexNet and vNet, a novel architecture designed to mimic the progressive increase in receptive field sizes along the human ventral stream. We show that training on ecoset leads to significant improvements in predicting representations in human higher-level visual cortex and perceptual judgments, surpassing the previous state of the art. Significant and highly consistent benefits are demonstrated for both architectures on two separate functional magnetic resonance imaging (fMRI) datasets and behavioral data, jointly covering responses to 1,292 visual stimuli from a wide variety of object categories. These results suggest that computational visual neuroscience may take better advantage of the deep learning framework by using image sets that reflect the human perceptual and cognitive experience. Ecoset and trained network models are openly available to the research community.
| S-EPMC7923360 | biostudies-literature