Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 6

Year

2021 1

2020 2

2019 1

2018 1

2017 1

Keywords

Question answering 2

A) sites 1

Answer selection 1

Attention 1

CO₂ conversion 1

Deep learning 1

Knowledge memory 1

Natural order 1

Needham’s Grand Question 1

Question and answering (Q& 1

Skip gram 1

Tagging 1

Temporality interaction 1

ancient Chinese scientific and technological achievements 1

comprehensive thinking 1

design dialectical methods 1

design driving innovation 1

design theoretical thinking 1

non-thermal plasma 1

open ︾

Search scope:

排序： Display mode:

Attention-based encoder-decoder model for answer selection in question answering Article

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 4, Pages 535-544 doi: 10.1631/FITEE.1601232

Abstract: One of the key challenges for question answering is to bridge the lexical gap between questions and answerspaper, we introduce an attention-based deep learning model to address the answer selection task for questionanswering.Our model also uses a step attention mechanism which allows the question to focus on a certain part ofIntegrating our model significantly improves the performance of our question answering system in the

Keywords： Question answering Answer selection Attention Deep learning

HTML PDF Collect

Temporality-enhanced knowledgememory network for factoid question answering Article

Xin-yu DUAN, Si-liang TANG, Sheng-yu ZHANG, Yin ZHANG, Zhou ZHAO, Jian-ru XUE, Yue-ting ZHUANG, Fei WU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1, Pages 104-115 doi: 10.1631/FITEE.1700788

Abstract: Question answering is an important problem that aims to deliver specific answers to questions posed byHow to efficiently identify the exact answer with respect to a given question has become an active linePrevious approaches in factoid question answering tasks typically focus on modeling the semantic relevanceor syntactic relationship between a given question and its corresponding answer.answering dataset from a trivia competition called quiz bowl.

Keywords： Question answering Knowledge memory Temporality interaction

HTML PDF Collect

Plasma-catalysis: Is it just a question of scale?

J. Christopher Whitehead

Frontiers of Chemical Science and Engineering 2019, Volume 13, Issue 2, Pages 264-273 doi: 10.1007/s11705-019-1794-3

Abstract: The issues of describing and understanding the changes in performance that result when a catalyst is placed into plasma are discussed. The different chemical and physical interactions that result and how their combination might produce beneficial results for the plasma-catalytic processing of different gas streams are outlined with particular emphasis being placed on the different range of spatial and temporal scales that must be considered both in experiment and modelling. The focus is on non-thermal plasma where the lack of thermal equilibrium creates a range of temperature scales that must be considered. This contributes in part to a wide range of inhomogeneity in different properties such as species concentrations and electric fields that must be determined experimentally by methods and be incorporated into modelling. It is concluded that plasma-catalysis is best regarded as conventional catalysis perturbed by the presence of a discharge, which modifies its operating conditions, properties and outcomes often in a very localised way. The sometimes used description “plasma-activated catalysis” is an apt one.

Keywords： plasma catalysis plasma-activated catalysis non-thermal plasma CO₂ conversion

HTML PDF Collect

Hybrid embedding and joint training of stacked encoder for opinion question machine reading comprehension

Xiang-zhou Huang, Si-liang Tang, Yin Zhang, Bao-gang Wei,huangxiangzhou@zju.edu.cn,siliang@zju.edu.cn,yinzh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 9, Pages 1267-1412 doi: 10.1631/FITEE.1900571

Abstract: Opinion question (MRC) requires a machine to answer questions by analyzing corresponding passages.Compared with traditional MRC tasks where the answer to every question is a segment of text in correspondingpassages, opinion question MRC is more challenging because the answer to an opinion question may notTo deal with imbalance of the dataset, irrelevancy of question and passage is used for .We are the biweekly champion in the opinion question MRC task in Artificial Intelligence Challenger 2018

HTML PDF Collect

Learning natural ordering of tags in domain-specific Q&A sites

Junfang Jia, Guoqiang Li,jiajunfang816@163.com,li.g@sjtu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 2, Pages 141-286 doi: 10.1631/FITEE.1900645

Abstract: is a defining characteristic of Web 2.0. It allows users of social computing systems (e.g., ) to use free terms to annotate content. However, is really a free action? Existing work has shown that users can develop implicit consensus about what tags best describe the content in an online community. However, there has been no work studying the regularities in how users order tags during . In this paper, we focus on the ing of tags in domain-specific Q&A sites. We study tag sequences of millions of questions in four Q&A sites, i.e., CodeProject, SegmentFault, Biostars, and CareerCup. Our results show that users of these Q&A sites can develop implicit consensus about in which order they should assign tags to questions. We study the relationships between tags that can explain the emergence of ing of tags. Our study opens the path to improve existing tag recommendation and Q&A site navigation by leveraging the ing of tags.

Keywords： Question and answering (Q& A) sites Tagging Natural order Skip gram

HTML PDF Collect

Establishing distinctive theories and methods of design science rooted in Chinese traditional culture

Huijun ZOU, Qinghua LIANG

Frontiers of Mechanical Engineering 2020, Volume 15, Issue 3, Pages 430-437 doi: 10.1007/s11465-019-0583-5

Abstract: The human social development saw the formation of five unique civilizations, with the latter forming their own distinctive cultures. China’s traditional culture is its most fundamental ideological weapon for solving problems. The Chinese are good at comprehensive thinking, dialectical thinking, and systematic analysis. These ideological weapons can solve the problems of formal science and technology and create scientific and technological achievements on par with global advanced scale. Ancient China is filled with original scientific and technological achievements, which strongly prove ancient China’s possession of its own science and technology different from that of Western Renaissance. Therefore, a comprehensive understanding of science, technology, experience, and intuition is necessary. The long-held superstition regarding the West, the lack of confidence, self-denial, blind imitation of ideas, and shackles must be thrown away. Only then can we take the road toward an authentic Chinese creative design as we learn from others.

Keywords： traditional Chinese culture comprehensive thinking systematic analysis Needham’s Grand Question ancient