Special Issue:Questions&Data for Better Science and Innovation Call for submissions

Editors Yang Wang,Xi'an Jiaotong University Dongbo Shi,Shanghai Jiaotong University Ye Sun,University College London Zhesi Shen,National Science Library,CAS Topic of the Special Issue What are the top questions towards better science and innovation and the required data to answer these questions?

MKEAH:Multimodal knowledge extraction and accumulation based on hyperplane embedding for knowledge-based visual question answering

Background External knowledge representations play an essential role in knowledge-based visual question and answering to better understand complex scenarios in the open world.Recent entity-relationship embedding approaches are deficient in representing some complex relations,resulting in a lack of topic-related knowledge and redundancy in topic-irrelevant information.Methods To this end,we propose MKEAH:Multimodal Knowledge Extraction and Accumulation on Hyperplanes.To ensure that the lengths of the feature vectors projected onto the hyperplane compare equally and to filter out sufficient topic-irrelevant information,two losses are proposed to learn the triplet representations from the complementary views:range loss and orthogonal loss.To interpret the capability of extracting topic-related knowledge,we present the Topic Similarity(TS)between topic and entity-relations.Results Experimental results demonstrate the effectiveness of hyperplane embedding for knowledge representation in knowledge-based visual question answering.Our model outperformed state-of-the-art methods by 2.12%and 3.24%on two challenging knowledge-request datasets:OK-VQA and KRVQA,respectively.Conclusions The obvious advantages of our model in TS show that using hyperplane embedding to represent multimodal knowledge can improve its ability to extract topic-related knowledge.

PAL-BERT:An Improved Question Answering Model

In the field of natural language processing(NLP),there have been various pre-training language models in recent years,with question answering systems gaining significant attention.However,as algorithms,data,and computing power advance,the issue of increasingly larger models and a growing number of parameters has surfaced.Consequently,model training has become more costly and less efficient.To enhance the efficiency and accuracy of the training process while reducing themodel volume,this paper proposes a first-order pruningmodel PAL-BERT based on the ALBERT model according to the characteristics of question-answering(QA)system and language model.Firstly,a first-order network pruning method based on the ALBERT model is designed,and the PAL-BERT model is formed.Then,the parameter optimization strategy of the PAL-BERT model is formulated,and the Mish function was used as an activation function instead of ReLU to improve the performance.Finally,after comparison experiments with traditional deep learning models TextCNN and BiLSTM,it is confirmed that PALBERT is a pruning model compression method that can significantly reduce training time and optimize training efficiency.Compared with traditional models,PAL-BERT significantly improves the NLP task’s performance.

Operational requirements analysis method based on question answering of WEKG

The weapon and equipment operational requirement analysis(WEORA) is a necessary condition to win a future war,among which the acquisition of knowledge about weapons and equipment is a great challenge. The main challenge is that the existing weapons and equipment data fails to carry out structured knowledge representation, and knowledge navigation based on natural language cannot efficiently support the WEORA. To solve above problem, this research proposes a method based on question answering(QA) of weapons and equipment knowledge graph(WEKG) to construct and navigate the knowledge related to weapons and equipment in the WEORA. This method firstly constructs the WEKG, and builds a neutral network-based QA system over the WEKG by means of semantic parsing for knowledge navigation. Finally, the method is evaluated and a chatbot on the QA system is developed for the WEORA. Our proposed method has good performance in the accuracy and efficiency of searching target knowledge, and can well assist the WEORA.

DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

基于Question Point的合作虚拟咨询服务

介绍了Question Point合作虚拟咨询服务产生的背景、功能、系统工作流程以及我国开展合作虚拟参考咨询的情况。

Question classification in question answering based on real-world web data sets

To improve question answering （QA） performance based on real-world web data sets,a new set of question classes and a general answer re-ranking model are defined.With pre-defined dictionary and grammatical analysis,the question classifier draws both semantic and grammatical information into information retrieval and machine learning methods in the form of various training features,including the question word,the main verb of the question,the dependency structure,the position of the main auxiliary verb,the main noun of the question,the top hypernym of the main noun,etc.Then the QA query results are re-ranked by question class information.Experiments show that the questions in real-world web data sets can be accurately classified by the classifier,and the QA results after re-ranking can be obviously improved.It is proved that with both semantic and grammatical information,applications such as QA, built upon real-world web data sets, can be improved,thus showing better performance.

Question Point——基于网络参考咨询系统的探讨

简要概述了Question Point的由来,讨论了其功能和在图书馆中的运作,同时提出了合作化数字参考咨询实施过程中的一些问题及未来的发展趋势。

Design of Questions in the Teaching of English Reading

Questions which were conventionally designed to check reading comprehension can also be used to enhance understanding. Different types of questions can be designed to achieve different purposes in reading. While designing questions, teachers should take into consideration such points as the language used, manner of presentation and types of questions etc. Moreover, once questions have been designed, it’s essential for teachers to think about the techniques for the use of these questions. If appro- priately used, questions contribute greatly to students’ understanding of what they’ re reading by helping to explore the meaning that language conveys, in addition to developing proper reading skills. Therefore, teachers should be able to teach reading with well-designed questions so that the ultimate goal of understanding the text is likely to be achieved.

Questioning Styles in Vocational College English Classrooms

This study investigates the effects of TBLT reform in Higher Vocational Colleges from the perspective of questioning styles.It employs three methods to collect data:classroom observation,semi-structured interviews and focus group discussion with eight English teachers and their 384 non-English major students from three Higher Vocational Colleges in Guangdong.The results indicated that the teachers assigned students different tasks to perform in class.They seemed to be adopting the TBLT approach,but their English classes were not totally different from the teacher-centered grammar-focused lessons,the student-centered or communicative lessons.

A Study on Teacher's Questioning Strategies in the UK

Classroom questioning is one of the main means for classroom interaction which plays a very important role in classroom teaching. Therefore, based on the observation of four different level English classes in the UK and interview of English teachers, this thesis investigates the types, functions and answer-seeking strategies used by EFL teachers.

Gender Differences In Using Questions——An Investigation of the Questions Used by Mr. Rochester and Jane in Jane Eyre

In literature,differences in the description of female and male characters have been noticeable for a long time.In this study,the novel Jane Eyre is uses as a material to investigate whether there are in fact any significant differences in the questions Mr.Rochester and Jane use and how the questions function to portray these two main characters.

基于渐进机器学习的中文问句匹配方法

问句匹配旨在判断不同问句的意图是否相近.近年来,随着大型预训练语言模型的发展,利用其挖掘问句对在语义层面隐含的匹配信息,取得了目前为止最好的性能.然而,由于基于独立同分布假设,在真实场景中,这些深度学习模型的性能仍然受制于训练数据的充足程度和目标数据与训练数据之间的分布漂移.本文提出一种基于渐进机器学习的中文问句匹配方法.该方法基于渐进机器学习框架,从不同角度提取问句特征,构建融合各类特征信息的因子图,然后通过迭代的因子推理实现从易到难的渐进学习.在特征建模中,设计并实现了两种类型特征的提取:(1)基于TF-IDF(Term frequency-inverse document frequency)的关键词特征;(2)基于DNN(Deep neural network)的深度语义特征.最后,通过通用的基准中文数据集LCQMC和BQ corpus验证了所提方法的有效性.实验表明,相比于单纯的深度学习模型,基于渐进机器学习的方法可以有效提升问句匹配的准确率,且其性能优势随着标签训练数据的减少而增大.

An Investigation of Teacher Questioning Strategies Usage in College English Course——A Case Study on Honghe University

Teacher questioning strategy is one of popular teaching method in teaching practice.The teachers and students of college English course II was taken as investigate objects in this study.This study will focus on the problems of questioning frequency,questioning types,questioning strategies,waiting time and students’response to deeply study this situation.Through the data collection and analysis,the researcher hopes the study will deeply reveal the real situation of teacher questioning usage in Honghe University.Some referential suggestions will be offered to the college English teachers for their future teaching.

英语Tag Question用法探究

TagQuestion(附加疑问句 ,也叫反意疑问句 )是英语中常用的疑问句式 ,主要用来提出情况和看法 ,并征求对方意见。文章就如何选配英语TagQuestion及其特殊用法做一简单探究。

Application of Questioning Strategy in English Reading Teaching

This paper mainly deals with the application of questioning strategy in English reading teaching.As one of the most useful methods,teachers usually attach great importance to questioning,which is proved to be very effective in teaching.

The Role of Questioning in the Teaching of Reading

In learner-centered classroom,teachers' questioning serves as very important stimuli to foster students' participation in classroom interaction.A classroom full of active interactions is an ideal environment for foreign language acquisition(FLA).Questioning is a critical strategy for the instructors to engage students in reading activities so as to help them build the habit of independent learning.

Teachers’Questioning Strategies in Reading Class—the Perspective of Adaptation

Teachers’questioning is one of the crucial means for classroom interaction.This study attempts to explore teachers’questioning strategies in reading class from the perspective of Adaptation Theory.It is found that the effective questioning can be realized in teachers’adaptation to their roles,the features of students and the features of reading courses.

loaded question与语言的间接性

在大学英语教学中会碰到很多值得研究的问题，下面这篇文章就是一个在教学备课中碰到的问题。尽管每本词典对loaded question的解释、翻译不一，但无论采用哪一种意思，它在语用学上都体现了语言的间接性。本文通过举例说明想把loaded question给阐释清楚，以期能为同样使用《大学体验英语》这一教材的同行或对这一问题感兴趣的人提供一些参考。

Question of culture五月初五端午节

韩国人拟申请将端午节的庆祝活动列入自己的文化遗产，中国人该怎么办?