scholarly journals Le Petit Prince: A multilingual fMRI corpus using ecological stimuli

2021 ◽  
Author(s):  
Jixing Li ◽  
Shohini Bhattasali ◽  
Shulin Zhang ◽  
Berta Franzluebbers ◽  
Wen-Ming Luh ◽  
...  
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Signal To Noise Ratio ◽  
English Speakers ◽  
Chinese Speakers ◽  
Correlation Data ◽  
Neural Substrate ◽  
Functional Analyses ◽  
The Brain ◽  
Limited Generalizability

ABSTRACTNeuroimaging using more ecologically valid stimuli such as audiobooks has advanced our understanding of natural language comprehension in the brain. However, prior naturalistic stimuli have typically been restricted to a single language, which limited generalizability beyond small typological domains. Here we present the Le Petit Prince fMRI Corpus (LPPC–fMRI), a multilingual resource for research in the cognitive neuroscience of speech and language during naturalistic listening (Open-Neuro: ds003643). 49 English speakers, 35 Chinese speakers and 28 French speakers listened to the same audiobook The Little Prince in their native language while multi-echo functional magnetic resonance imaging was acquired. We also provide time-aligned speech annotation and word-by-word predictors obtained using natural language processing tools. The resulting timeseries data are shown to be of high quality with good temporal signal-to-noise ratio and high inter-subject correlation. Data-driven functional analyses provide further evidence of data quality. This annotated, multilingual fMRI dataset facilitates future re-analysis that addresses cross-linguistic commonalities and differences in the neural substrate of language processing on multiple perceptual and linguistic levels.

scholarly journals The network properties of the brain at the time of normal birth support the acquisition of language processing

2018 ◽  
Author(s):  
Piergiorgio Salvan ◽  
Tomoki Arichi ◽  
Diego Vidaurre ◽  
J Donald Tournier ◽  
Shona Falconer ◽  
...  
Keyword(s):  
Language Acquisition ◽  
Language Processing ◽  
Developmental Trajectories ◽  
Brain Structures ◽  
Brain Network ◽  
Language Abilities ◽  
Normal Birth ◽  
Neural Substrate ◽  
Network Properties ◽  
The Brain

AbstractLanguage acquisition appears to rely at least in part on recruiting pre-existing brain structures. We hypothesized that the neural substrate for language can be characterized by distinct, non-trivial network properties of the brain, that modulate language acquisition early in development. We tested whether these brain network properties present at the normal age of birth predicted later language abilities, and whether these were robust against perturbation by studying infants exposed to the extreme environmental stress of preterm birth.We found that brain network controllability and integration predicted respectively phonological, ‘bottom-up’ and syntactical, ‘top-down’ language skills at 20 months, and that syntactical but not phonological functions were modulated by premature extrauterine life. These data show that the neural substrate for language acquisition is a network property present at term corrected age. These distinct developmental trajectories may be relevant to the emergence of social interaction after birth.

scholarly journals Automated Brain Tumor Prediction System using Natural Language Processing (NLP)

2021 ◽  
Vol 9 (VII) ◽  
pp. 3784-3787
Author(s):  
Gourav Sharma
Keyword(s):  
Brain Tumor ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Prediction System ◽  
Term Weighting ◽  
Linear Distance ◽  
Document Frequency ◽  
Maximum Similarity ◽  
The Brain

In this paper, we proposed an Automated Brain Tumor Prediction System which predicts Brain Tumor through symptoms in several diseases using Natural Language Processing (NLP). Term Frequency Inverse Document Frequency (TF-IDF) is used for calculating term weighting of terms on different disease’s symptoms. Cosine Similarity Measure and Euclidean Distance are used for calculating angular and linear distance respectively between diseases and symptoms for getting ranking of the Brain Tumor in the ranked diseases. A novel mathematical strategy is used here for predicting chance of Brain Tumor through symptoms in several diseases. According to the proposed novel mathematical strategy, the chance of the Brain Tumor is proportional to the obtained similarity value of the Brain Tumor when symptoms are queried and inversely proportional to the rank of the Brain Tumor in several diseases and the maximum similarity value of the Brain Tumor, where all symptoms of Brain Tumor are present.

scholarly journals A naturalistic neuroimaging database for understanding the brain using ecological stimuli

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Sarah Aliko ◽  
Jiawen Huang ◽  
Florin Gheorghiu ◽  
Stefanie Meliss ◽  
Jeremy I. Skipper
Keyword(s):  
Resting State ◽  
Signal To Noise Ratio ◽  
Data Driven ◽  
Functional Magnetic Resonance ◽  
Resonance Imaging ◽  
Complete Understanding ◽  
Movement Data ◽  
Good Signal ◽  
Functional Analyses ◽  
The Brain

Abstract Neuroimaging has advanced our understanding of human psychology using reductionist stimuli that often do not resemble information the brain naturally encounters. It has improved our understanding of the network organization of the brain mostly through analyses of ‘resting-state’ data for which the functions of networks cannot be verifiably labelled. We make a ‘Naturalistic Neuroimaging Database’ (NNDb v1.0) publically available to allow for a more complete understanding of the brain under more ecological conditions during which networks can be labelled. Eighty-six participants underwent behavioural testing and watched one of 10 full-length movies while functional magnetic resonance imaging was acquired. Resulting timeseries data are shown to be of high quality, with good signal-to-noise ratio, few outliers and low movement. Data-driven functional analyses provide further evidence of data quality. They also demonstrate accurate timeseries/movie alignment and how movie annotations might be used to label networks. The NNDb can be used to answer questions previously unaddressed with standard neuroimaging approaches, progressing our knowledge of how the brain works in the real world.

scholarly journals Detecting adverse events in clinical care using natural language processing

2019 ◽  
Author(s):  
Dorthe Klein ◽  
R.J.M.W. Rennenberg ◽  
F.A.G. van den Heuvel ◽  
R.P. Koopmans ◽  
M.H. Prins
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Medical Record ◽  
Language Processing ◽  
Medical Records ◽  
Signal To Noise Ratio ◽  
Clinical Care ◽  
Support Vector ◽  
Computer Algorithms ◽  
Svm Algorithm

Abstract Background Current methods for retrospective review of medical records require both time- and cost-wise a substantial effort. Therefore, we wanted to find the best method (based on natural language processing (NLP)) to select cases out of the medical records for further investigation in search for a (potentially preventable) adverse event (AE) to the decrease this effort. Methods The basic dataset consisted of 2987 medical records of patients who died during their hospitalization. To gain insight into the signal to noise ratio of the various resources, several subsets of our basic dataset were tested. Thereafter, we tested the scalability. After the best subset was chosen, several NLP algorithms were tested to select the best performing algorithm for the detecting of AEs. In the last experiment we tested the performance of the computer algorithms to predict potentially preventable AEs. The results of the NLP were compared with the outcome of the original retrospective medical record review. Results The dataset which contained he last three letters of the medical record showed the biggest potential. The scalability experiment showed that more data leads to a better performance of the algorithm. The best performing algorithm in the third test was the one based on support vector machine (SVM), with a precision of 79%, a negative predictive value (NPV) of 95% and a specificity of 85%. The results of the preventability experiment showed that the performance of the algorithms was almost equal to the results of the AEs. Conclusions In this study, we have shown that the SVM algorithm generates the most accurate results for the selection of cases for further investigation in the search for a (potentially preventable) AE. The sensitivity of the algorithms was around 75%. However, the SVM algorithm selected fewer cases to be examined for AEs compared to the original method. Consequently, this would lead to a lower workload for the committee. At the same time, there are a substantial number of cases, with potentially preventable AEs, not detected by machine learning.

scholarly journals A ‘Naturalistic Neuroimaging Database’ for understanding the brain using ecological stimuli

2020 ◽  
Author(s):  
Sarah Aliko ◽  
Jiawen Huang ◽  
Florin Gheorghiu ◽  
Stefanie Meliss ◽  
Jeremy I Skipper
Keyword(s):  
Resting State ◽  
Signal To Noise Ratio ◽  
Data Driven ◽  
Functional Magnetic Resonance ◽  
Resonance Imaging ◽  
Complete Understanding ◽  
Movement Data ◽  
Good Signal ◽  
Functional Analyses ◽  
The Brain

AbstractNeuroimaging has advanced our understanding of human psychology using reductionist stimuli that often do not resemble information the brain naturally encounters. It has improved our understanding of the network organization of the brain mostly through analyses of ‘resting-state’ data for which the functions of networks cannot be verifiably labelled. We make a ‘Naturalistic Neuroimaging Database’ (NNDb v1.0) publically available to allow for a more complete understanding of the brain under more ecological conditions during which networks can be labelled. Eighty-six participants underwent behavioural testing and watched one of 10 full-length movies while functional magnetic resonance imaging was acquired. Resulting timeseries data are shown to be of high quality, with good signal-to-noise ratio, few outliers and low movement. Data-driven functional analyses provide further evidence of data quality. They also demonstrate accurate timeseries/movie alignment and how movie annotations might be used to label networks. The NNDb can be used to answer questions previously unaddressed with standard neuroimaging approaches, progressing our knowledge of how the brain works in the real world.

scholarly journals Early acquisition of sign language

2010 ◽  
Vol 13 (2) ◽  
pp. 183-199 ◽  
Author(s):  
Evie Malaia ◽  
Ronnie B. Wilbur
Keyword(s):  
Language Acquisition ◽  
Natural Language ◽  
Sign Language ◽  
Language Processing ◽  
Brain Region ◽  
First Language ◽  
Sign Languages ◽  
Brain Functions ◽  
Early Acquisition ◽  
The Brain

Early acquisition of a natural language, signed or spoken, has been shown to fundamentally impact both one’s ability to use the first language, and the ability to learn subsequent languages later in life (Mayberry 2007, 2009). This review summarizes a number of recent neuroimaging studies in order to detail the neural bases of sign language acquisition. The logic of this review is to present research reports that contribute to the bigger picture showing that people who acquire a natural language, spoken or signed, in the normal way possess specialized linguistic abilities and brain functions that are missing or deficient in people whose exposure to natural language is delayed or absent. Comparing the function of each brain region with regards to the processing of spoken and sign languages, we attempt to clarify the role each region plays in language processing in general, and to outline the challenges and remaining questions in understanding language processing in the brain.

A Review and evaluation of Machine Translation methods for Lumasaaba

2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Research Area ◽  
Data Driven ◽  
East African ◽  
Data Set ◽  
African Languages ◽  
Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

Sign in / Sign up

Export Citation Format

Share Document