Generation of good-quality distractors is a key and time-consuming task associated withmultiple-choice questions(MCQs),one of the assessment items that have dominated the educational field for years.Recent advances in...Generation of good-quality distractors is a key and time-consuming task associated withmultiple-choice questions(MCQs),one of the assessment items that have dominated the educational field for years.Recent advances in language models and architectures present an opportunity for helping teachers to generate and update these elements to the required speed and scale of widespread increase in online education.This study focuses on a text-to-text approach for joints generation of distractors for MCQs,where the context,question and correct answer are used as input,while the set of distractors corresponds to the output,allowing the generation of three distractors in a singlemodel inference.By fine-tuning FlanT5 models and LongT5 with TGlobal attention using a RACE-based dataset,the potential of this approach is explored,demonstrating an improvement in the BLEU and ROUGE-L metrics when compared to previous works and a GPT-3.5 baseline.Additionally,BERTScore is introduced in the evaluation,showing that the fine-tuned models generate distractors semantically close to the reference,but the GPT-3.5 baseline still outperforms in this area.A tendency toward duplicating distractors is noted,although models fine-tuned with Low-Rank Adaptation(LoRA)and 4-bit quantization showcased a significant reduction in duplicated distractors.展开更多
The cloze test is constructed by deleting words from a selected passage and the examinees are required to complete broken patterns by filling in the blanks in order for the passage to make sense.It aims at testing exa...The cloze test is constructed by deleting words from a selected passage and the examinees are required to complete broken patterns by filling in the blanks in order for the passage to make sense.It aims at testing examinees'comprehensive language knowledge and skills.In this paper,the author analyzes items of a sample cloze test taken from CET6.展开更多
There are several types of cloze. The MC cloze is widely used in national examinations. MC cloze is similar to multiple choice, but not exactly the same. To develop an MC cloze, a suitable passage should be chosen fir...There are several types of cloze. The MC cloze is widely used in national examinations. MC cloze is similar to multiple choice, but not exactly the same. To develop an MC cloze, a suitable passage should be chosen first, then some of the words should be deleted, and finally the distractors for each item are set. To test whether the cloze is validable and reliable, the students are asked to take a pretest. The results are analyzed by GITEST. The data demonstrates that the difficulty level and the discrimination are not good enough. Some of the distractors are too tricky while some others are too weakly distractive.展开更多
In real-world scenarios,dual-view X-ray machines have outnumbered single-view X-ray machines due to their ability to provide comprehensive internal information about the baggage,which is important for identifying proh...In real-world scenarios,dual-view X-ray machines have outnumbered single-view X-ray machines due to their ability to provide comprehensive internal information about the baggage,which is important for identifying prohibited items that are not visible in one view due to rotation or overlap.However,existing work still focuses mainly on single-view,and the limited dual-viewbasedwork only performs simple information fusion at the feature or decision level and lacks effective utilization of the complementary information hidden in dual view.To this end,this paper proposes an end-to-end dual-view prohibited item detection method,the core of which is an adaptive material-aware coordinate-aligned attention module(MACA)and an adaptive adjustment strategy(AAS).Specifically,we observe that in X-ray images,the material information of an object can be represented by color and texture features,and remains consistent across views,even under complex backgrounds.Therefore,our MACA first integrates the material information of the prohibited items in each view and then smoothly transfers these clearmaterial clues along the shared axis to the corresponding locations in the other view to enhance the feature representation of the blurred prohibited items in the other view.In addition,AAS can autonomously adjust the importance of the two views during feature learning to make joint optimizationmore stable and effective.Experiments on the DvXray dataset demonstrate that the proposed MACA and AAS can be plug-and-played into various detectors,such as Faster Region-based Convolutional Neural Network(Faster R-CNN)and Fully Convolutional One-Stage Object Detector(FCOS),and bring consistent performance gains.The entire framework performs favorably against state-of-the-art methods,especially on small-sized prohibited items,highlighting its potential application in reality.展开更多
Loneliness is a complex and usually unpleasant emotional response to isolation,which has been considered the latest global health epidemic exacerbated by the coronavirus disease 2019 pandemic,affecting nearly twothird...Loneliness is a complex and usually unpleasant emotional response to isolation,which has been considered the latest global health epidemic exacerbated by the coronavirus disease 2019 pandemic,affecting nearly twothirds of older adults.Some profound health implications carried by loneliness include depression,cognitive impairment,hypertension and frailty.Across the world,there is no consensus definition of loneliness,and its measure is based on the phenomenological perspective of the individual.The 20-item University of California Los Angeles Loneliness Scale version 3(UCLA-20)is the most common measure.This scale demonstrates acceptable psychometric properties but is too long and complex for a phone interview.This paper addresses the increasing need to shorten this scale by adopting classical item response theory and network psychometrics to advance scale development.Through an item reduction analysis,we trimmed the original scale into an effective short form,which is as valid as the original one.With respondents’time at a premium in most research nowadays,this shortform scale is an efficient and practical alternative to the original UCLA-20.展开更多
基金supported by the Universidad de Alcalá(UAH)under Grant PIUAH21/IA-010Comunidad Autonóma de Madrid under Grant CM/JIN/2021-034.
文摘Generation of good-quality distractors is a key and time-consuming task associated withmultiple-choice questions(MCQs),one of the assessment items that have dominated the educational field for years.Recent advances in language models and architectures present an opportunity for helping teachers to generate and update these elements to the required speed and scale of widespread increase in online education.This study focuses on a text-to-text approach for joints generation of distractors for MCQs,where the context,question and correct answer are used as input,while the set of distractors corresponds to the output,allowing the generation of three distractors in a singlemodel inference.By fine-tuning FlanT5 models and LongT5 with TGlobal attention using a RACE-based dataset,the potential of this approach is explored,demonstrating an improvement in the BLEU and ROUGE-L metrics when compared to previous works and a GPT-3.5 baseline.Additionally,BERTScore is introduced in the evaluation,showing that the fine-tuned models generate distractors semantically close to the reference,but the GPT-3.5 baseline still outperforms in this area.A tendency toward duplicating distractors is noted,although models fine-tuned with Low-Rank Adaptation(LoRA)and 4-bit quantization showcased a significant reduction in duplicated distractors.
文摘The cloze test is constructed by deleting words from a selected passage and the examinees are required to complete broken patterns by filling in the blanks in order for the passage to make sense.It aims at testing examinees'comprehensive language knowledge and skills.In this paper,the author analyzes items of a sample cloze test taken from CET6.
文摘There are several types of cloze. The MC cloze is widely used in national examinations. MC cloze is similar to multiple choice, but not exactly the same. To develop an MC cloze, a suitable passage should be chosen first, then some of the words should be deleted, and finally the distractors for each item are set. To test whether the cloze is validable and reliable, the students are asked to take a pretest. The results are analyzed by GITEST. The data demonstrates that the difficulty level and the discrimination are not good enough. Some of the distractors are too tricky while some others are too weakly distractive.
基金by the Guangdong Basic and Applied Basic Research Foundation under Grant 2021B1515120064.
文摘In real-world scenarios,dual-view X-ray machines have outnumbered single-view X-ray machines due to their ability to provide comprehensive internal information about the baggage,which is important for identifying prohibited items that are not visible in one view due to rotation or overlap.However,existing work still focuses mainly on single-view,and the limited dual-viewbasedwork only performs simple information fusion at the feature or decision level and lacks effective utilization of the complementary information hidden in dual view.To this end,this paper proposes an end-to-end dual-view prohibited item detection method,the core of which is an adaptive material-aware coordinate-aligned attention module(MACA)and an adaptive adjustment strategy(AAS).Specifically,we observe that in X-ray images,the material information of an object can be represented by color and texture features,and remains consistent across views,even under complex backgrounds.Therefore,our MACA first integrates the material information of the prohibited items in each view and then smoothly transfers these clearmaterial clues along the shared axis to the corresponding locations in the other view to enhance the feature representation of the blurred prohibited items in the other view.In addition,AAS can autonomously adjust the importance of the two views during feature learning to make joint optimizationmore stable and effective.Experiments on the DvXray dataset demonstrate that the proposed MACA and AAS can be plug-and-played into various detectors,such as Faster Region-based Convolutional Neural Network(Faster R-CNN)and Fully Convolutional One-Stage Object Detector(FCOS),and bring consistent performance gains.The entire framework performs favorably against state-of-the-art methods,especially on small-sized prohibited items,highlighting its potential application in reality.
文摘Loneliness is a complex and usually unpleasant emotional response to isolation,which has been considered the latest global health epidemic exacerbated by the coronavirus disease 2019 pandemic,affecting nearly twothirds of older adults.Some profound health implications carried by loneliness include depression,cognitive impairment,hypertension and frailty.Across the world,there is no consensus definition of loneliness,and its measure is based on the phenomenological perspective of the individual.The 20-item University of California Los Angeles Loneliness Scale version 3(UCLA-20)is the most common measure.This scale demonstrates acceptable psychometric properties but is too long and complex for a phone interview.This paper addresses the increasing need to shorten this scale by adopting classical item response theory and network psychometrics to advance scale development.Through an item reduction analysis,we trimmed the original scale into an effective short form,which is as valid as the original one.With respondents’time at a premium in most research nowadays,this shortform scale is an efficient and practical alternative to the original UCLA-20.
