scholarly journals ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions

2018 ◽  
Author(s):  
Soham Parikh ◽  
Ananya Sai ◽  
Preksha Nema ◽  
Mitesh Khapra
Keyword(s):  
Reading Comprehension ◽  
Large Scale ◽  
State Of The Art ◽  
Multiple Choice ◽  
Multiple Choice Questions ◽  
Current State ◽  
New Information ◽  
Partial Elimination ◽  
Maximum Similarity ◽  
Option Selection

The task of Reading Comprehension with Multiple Choice Questions, requires a human (or machine) to read a given {passage, question} pair and select one of the n given options. The current state of the art model for this task first computes a question-aware representation for the passage and then selects the option which has the maximum similarity with this representation. However, when humans perform this task they do not just focus on option selection but use a combination of elimination and selection. Specifically, a human would first try to eliminate the most irrelevant option and then read the passage again in the light of this new information (and perhaps ignore portions corresponding to the eliminated option). This process could be repeated multiple times till the reader is finally ready to select the correct option. We propose ElimiNet, a neural network-based model which tries to mimic this process. Specifically, it has gates which decide whether an option can be eliminated given the {passage, question} pair and if so it tries to make the passage representation orthogonal to this eliminated option (akin to ignoring portions of the passage corresponding to the eliminated option). The model makes multiple rounds of partial elimination to refine the passage representation and finally uses a selection module to pick the best option. We evaluate our model on the recently released large scale RACE dataset and show that it outperforms the current state of the art model on 7 out of the 13 question types in this dataset. Further, we show that taking an ensemble of our elimination-selection based method with a selection based method gives us an improvement of 3.1% over the best-reported performance on this dataset.

scholarly journals Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions

2019 ◽  
Vol 33 ◽  
pp. 6276-6283 ◽  
Author(s):  
Zhipeng Chen ◽  
Yiming Cui ◽  
Wentao Ma ◽  
Shijin Wang ◽  
Guoping Hu
Keyword(s):  
Reading Comprehension ◽  
Mutual Information ◽  
Spatial Attention ◽  
State Of The Art ◽  
Multiple Choice ◽  
Multiple Choice Questions ◽  
Attention Model ◽  
Novel Approach ◽  
Proposed Model ◽  
Machine Reading

Machine Reading Comprehension (MRC) with multiplechoice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial Attention (CSA) model which can better handle the MRC with multiple-choice questions. The proposed model could fully extract the mutual information among the passage, question, and the candidates, to form the enriched representations. Furthermore, to merge various attention results, we propose to use convolutional operation to dynamically summarize the attention values within the different size of regions. Experimental results show that the proposed model could give substantial improvements over various state-of- the-art systems on both RACE and SemEval-2018 Task11 datasets.

scholarly journals Multi-Matching Network for Multiple Choice Reading Comprehension

2019 ◽  
Vol 33 ◽  
pp. 7088-7095 ◽  
Author(s):  
Min Tang ◽  
Jiaran Cai ◽  
Hankz Hankui Zhuo
Keyword(s):  
Reading Comprehension ◽  
Correct Answer ◽  
Large Scale ◽  
State Of The Art ◽  
Multiple Choice ◽  
Semantic Relationship ◽  
Matching Network ◽  
Empirical Results ◽  
Proposed Model ◽  
Machine Reading

Multiple-choice machine reading comprehension is an important and challenging task where the machine is required to select the correct answer from a set of candidate answers given passage and question. Existing approaches either match extracted evidence with candidate answers shallowly or model passage, question and candidate answers with a single paradigm of matching. In this paper, we propose Multi-Matching Network (MMN) which models the semantic relationship among passage, question and candidate answers from multiple different paradigms of matching. In our MMN model, each paradigm is inspired by how human think and designed under a unified compose-match framework. To demonstrate the effectiveness of our model, we evaluate MMN on a large-scale multiple choice machine reading comprehension dataset (i.e. RACE). Empirical results show that our proposed model achieves a significant improvement compared to strong baselines and obtains state-of-the-art results.

scholarly journals Using plants to remediate or manage metal-polluted soils: an overview on the current state of phytotechnologies

2021 ◽  
Vol 43 ◽  
pp. e58283
Author(s):  
Clístenes Williams Araújo do Nascimento ◽  
Caroline Miranda Biondi ◽  
Fernando Bruno Vieira da Silva ◽  
Luiz Henrique Vieira Lima
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Cost Effective ◽  
Time Frame ◽  
Contaminated Site ◽  
Polluted Soils ◽  
Mining Sites ◽  
Current State ◽  
Remedial Actions ◽  
The Tropics

Soil contamination by metals threatens both the environment and human health and hence requires remedial actions. The conventional approach of removing polluted soils and replacing them with clean soils (excavation) is very costly for low-value sites and not feasible on a large scale. In this scenario, phytoremediation emerged as a promising cost-effective and environmentally-friendly technology to render metals less bioavailable (phytostabilization) or clean up metal-polluted soils (phytoextraction). Phytostabilization has demonstrable successes in mining sites and brownfields. On the other hand, phytoextraction still has few examples of successful applications. Either by using hyperaccumulating plants or high biomass plants induced to accumulate metals through chelator addition to the soil, major phytoextraction bottlenecks remain, mainly the extended time frame to remediation and lack of revenue from the land during the process. Due to these drawbacks, phytomanagement has been proposed to provide economic, environmental, and social benefits until the contaminated site returns to productive usage. Here, we review the evolution, promises, and limitations of these phytotechnologies. Despite the lack of commercial phytoextraction operations, there have been significant advances in understanding phytotechnologies' main constraints. Further investigation on new plant species, especially in the tropics, and soil amendments can potentially provide the basis to transform phytoextraction into an operational metal clean-up technology in the future. However, at the current state of the art, phytotechnology is moving the focus from remediation technologies to pollution attenuation and palliative cares.

scholarly journals MSK30: a validated tool to assess clinical musculoskeletal knowledge

2019 ◽  
Vol 5 (1) ◽  
pp. e000495
Author(s):  
Danielle L Cummings ◽  
Matthew Smith ◽  
Brian Merrigan ◽  
Jeffrey Leggit
Keyword(s):  
Medical Students ◽  
Large Scale ◽  
Assessment Tool ◽  
Multiple Choice ◽  
School Curriculum ◽  
Average Score ◽  
Multiple Choice Questions ◽  
Modified Delphi ◽  
Multiple Choice Exam ◽  
Individual Education

BackgroundMusculoskeletal (MSK) complaints comprise a large proportion of outpatient visits. However, multiple studies show that medical school curriculum often fails to adequately prepare graduates to diagnose and manage common MSK problems. Current standardised exams inadequately assess trainees’ MSK knowledge and other MSK-specific exams such as Freedman and Bernstein’s (1998) exam have limitations in implementation. We propose a new 30-question multiple choice exam for graduating medical students and primary care residents. Results highlight individual deficiencies and identify areas for curriculum improvement.Methods/ResultsWe developed a bank of multiple choice questions based on 10 critical topics in MSK medicine. The questions were validated with subject-matter experts (SMEs) using a modified Delphi method to obtain consensus on the importance of each question. Based on the SME input, we compiled 30 questions in the assessment. Results of the large-scale pilot test (167 post-clerkship medical students) were an average score of 74 % (range 53% – 90 %, SD 7.8%). In addition, the tool contains detailed explanations and references were created for each question to allow an individual or group to review and enhance learning.SummaryThe proposed MSK30 exam evaluates clinically important topics and offers an assessment tool for clinical MSK knowledge of medical students and residents. It fills a gap in current curriculum and improves on previous MSK-specific assessments through better clinical relevance and consistent grading. Educators can use the results of the exam to guide curriculum development and individual education.

scholarly journals QASC: A Dataset for Question Answering via Sentence Composition

2020 ◽  
Vol 34 (05) ◽  
pp. 8082-8090
Author(s):  
Tushar Khot ◽  
Peter Clark ◽  
Michal Guerquin ◽  
Peter Jansen ◽  
Ashish Sabharwal
Keyword(s):  
Common Sense ◽  
Human Performance ◽  
Question Answering ◽  
State Of The Art ◽  
Multiple Choice ◽  
Training Data ◽  
Language Models ◽  
Current State ◽  
New Concepts ◽  
Large Corpus

Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice question. QASC is the first dataset to offer two desirable properties: (a) the facts to be composed are annotated in a large corpus, and (b) the decomposition into these facts is not evident from the question itself. The latter makes retrieval challenging as the system must introduce new concepts or relations in order to discover potential decompositions. Further, the reasoning model must then learn to identify valid compositions of these retrieved facts using common-sense reasoning. To help address these challenges, we provide annotation for supporting facts as well as their composition. Guided by these annotations, we present a two-step approach to mitigate the retrieval challenges. We use other multiple-choice datasets as additional training data to strengthen the reasoning model. Our proposed approach improves over current state-of-the-art language models by 11% (absolute). The reasoning and retrieval problems, however, remain unsolved as this model still lags by 20% behind human performance.

AN APPLICATION CONCEPT OF THE FIBRE-OPTICAL TECHNOLOGY IN GEODETIC MONITORING OF ENGINEERING OBJECTS

2017 ◽  
Vol 166 (46) ◽  
pp. 60-74
Author(s):  
Krzysztof Karsznia ◽  
Konrad Podawca
Keyword(s):  
Risk Management ◽  
Large Scale ◽  
State Of The Art ◽  
Monitoring Systems ◽  
Management Approach ◽  
Engineering Structures ◽  
Geoinformation Systems ◽  
Current State ◽  
Modern Engineering ◽  
Integrated Risk

Monitoring of structures and other different field objects undoubtedly belongs to the main issues of modern engineering. The use of technologies making it possible to implement structural monitoring makes it possible to build an integrated risk management approach combining instrumental solutions with geoinformation systems. In the studies of engineering structures, there is physical monitoring mainly used for examining the physical state of the object - so-called SHM ("Structural Health Monitoring"). However, very important role is also played by geodetic monitoring systems (GMS). The progress observed in the field of IT and automatics has opened new possibilities of using integrated systems on other, often large-scale objects. Based on the current state-of-the-art, the article presents the concept of integration approaches of physical and geodetic monitoring systems in order to develop useful guidelines for further construction of an expert risk management system.

Real Time Simulation for High Fidelity Multibody Dynamics and Mechatronic Systems

2014 ◽  
Author(s):  
William Prescott
Keyword(s):  
Real Time ◽  
Multibody Dynamics ◽  
Large Scale ◽  
State Of The Art ◽  
High Fidelity ◽  
Implicit Integration ◽  
Mechatronic Systems ◽  
Vehicle Simulation ◽  
Current State ◽  
Time Simulation

This paper will investigate the use of large scale multibody dynamics (MBD) models for real-time vehicle simulation. Current state of the art in the real-time solution of vehicle uses 15 degree of freedom models, but there is a need for higher-fidelity systems. To increase the fidelity of models uses this paper will propose the use of the following techniques: implicit integration, parallel processing and co-simulation in a real-time environment.

scholarly journals OPTIMIZING STUDENTS’ READING COMPREHENSION OF DESCRIPTIVE TEXT THROUGH E-LEARNING METHOD WITH WHATSAPP APPLICATION AT STUDENTS OF SMA NEGERI 1 BUKO

2021 ◽  
Vol 9 (1) ◽  
pp. 1-16
Author(s):  
Yustira Kharlina Tangiduk ◽  
Nurmin Samola ◽  
Rinny Rorimpandey
Keyword(s):  
Reading Comprehension ◽  
Data Analysis ◽  
Standard Deviation ◽  
Frequency Distribution ◽  
Multiple Choice ◽  
Learning Method ◽  
Multiple Choice Questions ◽  
E Learning ◽  
The Mean ◽  
Academic Year

This study aims to determine whether the E-learning method can be effective in optimizing students' reading comprehension of descriptive text with WhatsApp Application. This research was conducted in class X MIA 1 SMA Negeri 1 Buko in the academic year of 2020/2021. This study used one group-pretest-postest design of research with the data analysis were the frequency distribution of scores, mean and standard deviation. The questions from the pretest and posttest used the type of multiple choice questions with questions about the descriptive text. From this result, it was found that the mean of posttest Y = 7.8 with standard deviation Sy = 0.79 was higher than mean score at pretest X = 5.33 with standard deviation Sx = 0.89. It means that students' reading comprehension in descriptive text was higher after treatment at posttest than pretest. So the researcher concluded that the application of the E-learning method through WhatsApp application was effective in optimizing students' reading comprehension of descriptive text.

scholarly journals Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series

2021 ◽  
Vol 13 (22) ◽  
pp. 4599
Author(s):  
Félix Quinton ◽  
Loic Landrieu
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Crop Rotation ◽  
Large Scale ◽  
State Of The Art ◽  
Crop Rotations ◽  
Learning Approach ◽  
Type Mapping ◽  
Current State ◽  
Crop Type

While annual crop rotations play a crucial role for agricultural optimization, they have been largely ignored for automated crop type mapping. In this paper, we take advantage of the increasing quantity of annotated satellite data to propose to model simultaneously the inter- and intra-annual agricultural dynamics of yearly parcel classification with a deep learning approach. Along with simple training adjustments, our model provides an improvement of over 6.3% mIoU over the current state-of-the-art of crop classification, and a reduction of over 21% of the error rate. Furthermore, we release the first large-scale multi-year agricultural dataset with over 300,000 annotated parcels.

Sign in / Sign up

Export Citation Format

Share Document