Author: yuhang Liu

04/29/2020 – Yuhang Liu – VisiBlends: A Flexible Workflow for Visual Blends

yuhang Liu 1 Comment

Summary:

This article is devoted to researching a flexible system to complete visual blends. Visual blends is an advanced graphic design technology designed to attract people’s attention. It combines two objects together, which has applications in many fields, because it can express information well. However, visual blends do not simply combine or paste the two pictures together. It need to combine the characteristics of the two images, and it also need to be able to separate the two images. The previous working methods have some drawbacks, such as assigning tasks to a work fixedly person. Therefore, the author of this paper proposes a new workflow that can achieve flexible visual blends. The workflow of the system decomposes the flow of integrated computing technology and human microtasks, so that users can collectively generate visual fusion through brainstorming, synthesis and iterative steps. The workflow includes: brainstorming, Finding Images, Annotate Images for Shape and Coverage, Matching Algorithm, Automatic Blend Synthesis and Evaluation.

Reflection:

Before reading each article, I will anticipate the method of the article from the title of the article. Also before reading this article, I am thinking about how to implement a flexible workflow for visual blends. I think that when combining two images to form a new image and complete a new idea, increasing the flexibility of the workflow requires a wider selection of pictures and the order of work that can be changed, for example, to determine the images then to achieve the purpose, or determine a purpose, and then find two images. But I have never thought about starting from the worker’s perspective, through the participation of more workers, to build a flexible workflow.

And, I think the more important benefit of introducing brainstorming is inspiring workers. Compared to the method I mentioned before, and combined with real life, when completing a creative task, inspiration is the most difficult to find. So I think this is indeed a very good way. The benefits of setting up the first step of the system as brainstorming are:

  1. Help workers better understand the purpose of the task, which is not limited to the purpose of the current task, and at the same time, the understanding of visual blends can also be improved.
  2. Inspire inspiration. In the multi-person work style, people can choose the tasks they want to do, and can look at the results of others, and even collaborate with each other, which is very helpful for the construction of ideas.

So I think that this system has improved the flexibility of inspiring ideas and work. At the same time, because of the introduction of annotations, merge two images by computers and the evaluation system, I think the quality can be guaranteed in all aspects. But I think there are some limitations, for example, the generation of the machine may not control some details, but I think that a good design must pay great attention to details.

Question:

  1. Do you think this system can realize a flexible workflow, or it is more inclined to a heuristic system.
  2. How the system should control the details of the images automatically synthesized by the machine
  3. What are the limitations of this system?

Read More

04/29/2020 – Yuhang Liu – Accelerating Innovation Through Analogy Mining

yuhang Liu 1 Comment

Summary:

This article is similar to a previous paper “SOLVENT: A Mixed Initiative System for Finding Analogies between Research Papers” in that it focuses on how to search for articles in a vast corpus of papers. In the massive essay library, constantly get ideas. The research method of this paper is based on previous papers and previous papers with some changes. In previous papers, this system of discovering new ideas by analogy usually requires an understanding of the deep similarity between two entities, and then comparison or research, However, finding analogies is challenging for machines, as it is based on having an understanding of the deep relational similarity between two entities that may be very different in terms of surface attributes, and in previous studies there were methods based on similarity, such as TF-IDF, LSA, LDA, and GloVe, but the authors of this paper investigate a weaker structural representation, the goal is to come up with a representation that can be learned, while still being expressive enough to allow analogical mining. So the method proposed in this article requires crowdsourced workers to annotate the purpose and mechanism of a paper. Then through learning and systematic research, new ideas for similar purposes but through different mechanisms are obtained. And from the test, the authors found it has a better effect than other methods.

Reflection:

First of all, on the basis of reading another paper on a similar subject, I want to make a comparison between the two articles. In another article, People need to analyze an article from four aspects, Background, Purpose, Mechanism, Findings. Then the machine generates an analogy by comparing and learning these four structural aspects. In this article, a paper is divided into two parts, the purpose and the mechanism, which is also called as a relatively weak structured representation. Separating an idea into purpose and mechanisms enables core analogical innovation processes such as repurposing. So the final experiment in this article is also based on the same purpose, different mechanism. So, there are only two dimensions to represent a paper which is more abstract and broad, and directly learn them in a supervised method. The benefits of doing this is, it is possible to automatically extract these representations from product descriptions for potential wide applicability. Identifying key components and functions can also improve the search function of the system and better understand the needs of users.

Secondly, I think the most important thing about a system that finds analogies between papers or products is its feasibility, which is reason why I think the method in this paper is better. In terms of the feasibility of the system, letting a crowdsourced worker or machine discover the purpose and mechanism of an article described in a paper is far simpler than analyzing the structure (background, purpose, mechanism, finding) of an article, and there will be less errors in the simple tasks, so a better data sets will be available for learning. At the same time, in terms of the feasibility of the ideas that are formed, the system introduces graduate students to comprehensively judge the feasibility of ideas. From my aspect, this is particularly important, if an idea is unrealizable or cannot withstand the test , then no matter how novel, it is useless. So in my opinion this is the advantage of the system.

But at the same time, I have some doubts about the results of the system, because the system seems to be more inclined to find the different mechanism for the same purpose. For different purposes, the idea of the same mechanism seems difficult to obtain. And I think that the most difficult part of innovation is to apply an idea to a new field, and the examples of bionics that we think of most are: fish float and submarine, bat and radio. In my opinion, those inventions that have a significant impact on people’s lives are usually the application of mechanisms in other fields to achieve new goals. So for an unresearched field or unrealized purpose, I think these can be used as the direction of future research of the method.

Question:

  1. What are the limitations do you think of the method proposed in this article?
  2. What methods do you think can be used to evaluate the usefulness of analogy ideas?
  3. What do you think is more important for the idea of finding an analogy, surface similarity, structural similarity, or some other factors?

Read More

04/22/2020 – Yuhang Liu – Opportunities for Automating Email Processing: A Need-Finding Study

yuhang Liu 2 Comments

Summary:

This article discusses the e-mail management system. It is well known that e-mail has very important position in our lives, so the authors have developed a platform to help manage e-mail in order to make e-mail severs better. The authors have implemented methods that need study to learn: (i) what kind of automatic e-mails do users want, and (ii)what kinds of information and computation are needed to support that automation. The authors conducted three surveys: designing a workshop to identify categories of needs, conducting surveys to better understand these categories, and classifying existing email automation software to determine the needs that have been resolved. The authors ’results highlight the need to strengthen the following aspects in order to better automate the management of mail: richer data, more management attention, use of internal and external email contexts, complex processing (such as response summarization) and affordance senders. Finally, the authors developed a platform for writing small scripts on user inboxes. In their research, we found that most of the popular mail services are not enough to support automated management, which also supports us to develop new mail services.

Reflection:

First of all, from my personal experience, I agree with that we need a system that can help people manage email to reduce the energy people spend in this regard. Usually during my studies or work. If there is a new e-mail, I usually go to deal with the mail first, which is seriously affected the work efficiency. So a system to help manage mail is very necessary. And I also agree that the authors use three probes to study the needs of the mail management system. Among them, I think there are several requirements that are really urgent, such as richer data model for rules and the leveraging of internal and external email contexts. The richer data model helps to study the content and format of the email. For example, we have another article this week. Marking the structure of the article through people can help the machine to understand the article. Similarly, more email formats and templates Can help the machine understand the mail. And studying the internal and external emails can also better understand the content of the email, and at the same time understand the relationship between the sender and the user. These can be greatly improved. But I have doubts about the system mentioned in the article and the future development direction. Because researching the content of emails and users, especially such in-depth research, I think that it will intrude the privacy of users, and at the same time, I think that the accuracy of management cannot be guaranteed, so the wider application may bring more problems. As an example, I often find that some of the mails that I think are important are considered as spam and enter the spam box and make me miss many things. But I think the author proposes to make people customize in the text is a good solution, however for those who are not familiar with computer applications, whether such customization is really beneficial to their use is also a question and worth thinking about.

Question:

  1. What aspects of the current popular mail service system needs to be improved?
  2. If we want to build an automating e-mail processing system, do you think we need a brand new framework, or change slowly based on the existing service system?
  3. Will automating processing of e-mail cause other problems?

Read More

04/22/2020 – Yuhang Liu – SOLVENT: A Mixed Initiative System for Finding Analogies between Research Papers

yuhang Liu 2 Comments

Summary:

This paper mainly talks about a new paper search system, and I think that it can be thought as a thought initiation system rather than a paper search system. The article first proposes that scientific discovery is usually promoted by finding analogies in distant fields, but as more and more papers are published now, it is difficult to find papers with relevant ideas in a field, even though in those cross-field. Therefore, in order to achieve this aim, the authors introduced a hybrid system. In this system, crowdsourcing workers are mainly responsible for reading and understanding an article. People need to analyze an article from four aspects, Background, Purpose, Mechanism, Findings. The computer then analyzes the article based on these semantic frameworks, such as through TFIDF, or a combination of different architectures, and then finds similar usages from research papers. And through verification, found that these annotations are more effective, and can help experts.

Reflection:

First of all, I agree with the goal of the thesis, helping more researchers to obtain new ideas by analogy from outside the field, and then use these ideas and innovative ideas to promote the development of science and technology. I also think that analogies can help technology anyway. The article also cited quite a few examples to show the effectiveness of analogy and the breakthrough of research after the analogy. And in my reading in the past few weeks, I often feel that the article uses analogy. Since then, I have been thinking about how to help people more effectively through analogy and learn from other subject areas. Secondly, I think it is a very effective method to introduce people to assist in the completion. This is also the biggest gain in the course of my word. When a problem is encountered, the consideration is to use human power to solve it. And in the article, let the crowd source workers to annotate the article from four directions, I think it can greatly decompose an article, so that the computer can better understand this article. It is still difficult for a computer to directly understand an article and find out from it, but based on these architectures, finding the connection between articles is indeed a relatively simple task. But at the same time, I have some doubts about the effectiveness of the system proposed in the article. The article also spent a considerable amount of space to describe the limitations of this system. And my doubts are mainly focused on the third point, the usefulness in the real world. I think there are many aspects that will affect this practicality. For example, when the data increases, there will be more similar analogies, and the quality of these analogies is difficult to control. As we know, not all the lessons are useful, some ideas may bring Other problems, such as reduced efficiency, wasted resources, etc. The final point is that I think it takes a lot to get a good idea. We also need to control the quality of the work done by the workers and whether the algorithm can be so enlightening. In my opinion, a good innovation is usually electro-optical flint. Although this may be relatively easy to achieve on the basis of analogy, it still needs a good collaboration between human and machine to complete.

Question:

  1. Do you think finding analogy by analyze papers based on their framework is a useful way?
  2. Is there any other factors might influence this system, such as the increase of similar articles or different understanding between workers?
  3. Except the methods mentioned in the article, as computer scientists, what can we do to inspire people?

Read More

04/15/2020 – Yuhang Liu – Algorithmic Accountability Journalistic investigation of computational power structure

yuhang Liu Leave a comment

Summary: in this paper, the author has mentioned that, in modern society, automated algorithms have become more and more important, and algorithms gradually regulate all aspects of our lives, but the outline of their functions may still be difficult to grasp. So, it is necessary to elucidating and articulating the algorithms’ power. The author proposes a new notion “algorithmic accountability reporting”. This concept can reveal how algorithms work, and it is well worth reviewing by computing journalists. The author explores methods such as transparency and reverse engineering, and how they can be useful in elucidating algorithmic capabilities. And the author analyzes the case studies of five journalists on algorithm research, and describes the challenges and opportunities they face when working on algorithm accountability. The final concept proposed by the author has highlights and main contributions: (1) It proposed the theoretical lens of various atomic algorithm decisions. These decisions raised some major issues that can guide algorithm research and algorithm transparency policy development. (2) It can conduct preliminary evaluation and analysis of the algorithm through algorithmic accountability, including various restrictions. and author discuss the challenges faced in adopting this reporting method, including human resources, legitimacy and ethics, and look ahead to how journalists themselves use transparency when using algorithms

Reflection: I think the author has put forward a very innovative idea. This is also the first point that comes to my mind when I meet or use some new algorithms: what is the boundary of this algorithm, and what scope can it be applied to. For example, the insurance algorithm of an insurance company, we all know that the insurance cost is generated based on a series of attributes, but people are often uncertain about the proportion of each attribute in the insurance algorithm, then there will be some doubts about the results, and even think some results are immoral. Therefore, it is very important to study the capabilities and boundaries of an algorithm.

At the same time, the concept of reverse engineering is mentioned in the article, that is, the ability to study algorithms by studying input and output, but there are often such mechanisms in some websites. It makes the algorithm dynamic, so we need other methods to solve this kind of problem. However, once the input-output relationship of the black box is determined, the challenge becomes a data-driven search for news stories. Therefore, I think the algorithm is more inclined to understand whether there is an unreasonable situation in an algorithm, and the root cause of this unreasonable situation is whether it is caused by man or negligence, or it is people’s deep-rooted ideas . So, in some aspects, I think exploring the borders of algorithms is exploring the morality of algorithms. Therefore, I think this article provides a framework for reviewing the morality of the algorithm. This method can effectively explore a place where the algorithm is unreasonable, and for news reporters, it can be used to discover meaningful news.

In addition, I think the framework described in this article is a special way of human-computer interaction, that is, people study the machine itself, and understand the process of algorithm operation through the feedback of the machine. This also broadened my understanding of human-computer interaction.

Problem:

  1. Do you think the framework mentioned in the paper can be used in detecting the ethic issues of an algorithm?
  2. Can this system be used in a automatic system to elucidating and articulating the algorithms’ power?
  3. Is there any other value of detecting algorithms’ power except news value?

Read More

04/15/2020 – Yuhang Liu – Believe it or not: Designing a Human-AI Partnership for Mixed-Initiative Fact-Checking

yuhang Liu 2 Comments

Summary:

This article discusses a system about fact detection. First of all, the article proposes that fact detection is a very important, challenging and time-sensitive. Usually, in this type of system, the human influence on the system is ignored, but the human influence is very important in this type of system. Therefore, this article establishes a hybrid startup system for fact checking. Enable users to interact with ML predictions to complete challenging fact checks. The author designed the interface through which the user can know the source of the prediction. In some applications, when the users know the prediction results but is not satisfied, the author also allows the user to use his own beliefs or inferences to cover these predictions. Through this system, the authors have come to a conclusion that when the model’s results are correct, these predictions will have a very positive impact on people. However, people should not overly trust the model’s predictions, when users think the predictions is wrong, the prediction result can be improved through interactive methods. And this also reflects the importance of a transparent, interactive system for fact detection from the side.

Reflection:

When I saw the title of this article, I thought that this article maybe have a same topic with my project, using crowdsourced workers to distinguish fake news, but when I read it to a certain extent, I found that this is not the case. But I think it affirmed my thinking in some aspects. First, fact detection is a very challenging project, especially when real-time is needed, so it is very necessary to rely on human power, and due to lack of Marked data, so if you want to directly complete the task through machine learning, in some cases, the prediction results will point in a completely opposite direction. For example, in my project, rumors and refuting rumors are both may be considered as a rumor, so we need crowd workers to distinguish it.

Secondly, for the project itself mentioned in the article, I think its method is a very good direction. First of all, human judgment is particularly important in this kind of system. This is also the main idea of many human-computer interaction systems to improve accuracy through humans. I think this method in the article is a good start. In a transparent system, let people decide whether to cover the forecast results. Not only do they not force people to participate in the system, but also let people make predictions There are very important weights.

But at the same time, I think the system also has some of the limitations described in the article. For example, the purpose of crowdsourcing workers and its own concerns may affect the results of the final system, so I think the article proposes a good direction, but we need to be more Careful research.

Problem:

  1. Do you think users usually can find the prediction is incorrect and cover it when a system is wrong?
  2. What role does the transparency of the system play in the interaction?
  3. How to prevent users trust the prediction too far in other human and computer interaction systems?

Read More

04/08/2020 – Yuhang Liu – CrowdScape: Interactively Visualizing User Behavior and Output

yuhang Liu Leave a comment

Summary:

This article proposes that the crowdsourcing platform is a very good tool and can help people solve quite a few problems. It can help people quickly allocate work and complete tasks on a large scale. Therefore, the work quality of the workers on the crowdsourcing platform is very important. In the previous research, other researchers have developed algorithms on the inspection of the workers ’work quality and the workers’ behavior to detect the workers ’work quality, but these algorithms are all It has limitations, especially those complex tasks. The manual assessment of the quality of tasks completed by workers can solve this problem, but when many workers are needed, it cannot be scaled well. Therefore, based on this background, the author created CrowdScape, which can support the inspection of the work quality of crowdsourced workers through interactive visualization and hybrid active machine learning. The system’s approach is to combine information about worker behavior and worker output to better explain the work of the workers. This system mainly completes the exploration of workers’ work quality through the development and application of the following functions. : 1 Build an interface that can interactively browse the results of crowd workers, and explain the performance of workers by combining the information of workers’ behavior and output 2 Can visualize the behavior of mass workers 3 Can explore the products of mass workers 4 Tools for grouping and classifying workers 5 Combine machine learning to guide users’ intuition to the masses.

Reflection:

The system introduced in this article has many innovations, the most important of which is the ability to combine the behavior of workers with the output of workers, which is beneficial to study the behavior of workers with different performances. This is what we often say that the result is determined by the process. The author incorporates this into the research. I think it is a very innovative point, through this vigorous research, we can get the working behavior of workers with different results, and in the subsequent research, we can not only focus on workers with good output. The more important meaning is that the behavior guidance can be summarized through the behavior of workers with good output, and the behavior guidance can be used to guide the workers to complete the task better. And another innovation point I think is to visualize the interactive process. As we all know, people can better receive visual information. I think this is also feasible when evaluating the work effect of crowdsourced workers. Visualizing the interaction process of crowdsourced workers can help people better study the behavior of workers, and at the same time can improve people’s understanding of the performance of crowdsourced workers at work, and it also help us design ideas for crowdsourcing tasks. At the same time, the system’s dynamic query system can quickly analyze large data sets by providing users with immediate feedback. I think Crowddscape is based on these points in order to better discover people’s work patterns and understand the essence of crowdsourcing. And constantly adapt to more complex and innovative crowdsourcing tasks.

Question:

  1. Whether the quality of workers ’work must be related to behavior, and how the system prevents some workers achieving good results with inappropriate behavior?
  2. When workers know their behavior will be recorded, if it will affect their work?
  3. Is there any other method to lead workers to have a better output?

Read More

04/08/2020 – Yuhang Liu – Agency plus automation: Designing artificial intelligence into interactive systems

yuhang Liu Leave a comment

Summary:

This article discusses the relationship between artificial intelligence and staff. First of all, in modern society, with the rapid development of technology, the continuous development of artificial intelligence makes people more and more inclined to use the latest artificial intelligence to replace real people, but These ideas are usually based on very optimistic situations and underestimate the challenges of applying artificial intelligence. In general, artificial intelligence cannot complete these tasks without human resources. Therefore, in this case, we need to change our thinking. If we are not able to completely constitute automated technology to liberate human resources, then we can build computing auxiliary functions to strengthen and enrich people’s intellectual work. Therefore, the author of this article proposes to build a system that can realize rich interaction between people and algorithms. The system in this article is not intended to liberate the manpower in some systems. On the contrary, it is hoped that these manpower can be strengthened to better play the role of man in a system. This system balances the advantages of all aspects while promoting human control and action. The author applies this system to three aspects, and integrates the active computing in the interactive system to explain that this system is useful and can achieve the purpose of enhancing manpower. Finally, the author discusses the possibility of its future application.

Reflection:

I think the author ’s idea is very innovative. First of all, I have to admit that it is very difficult to fully implement the automation function. In my recent project, I have obvious feelings. In the natural scene, there is no labeled tweets whether it is a rumor. To implement supervised learning to automatically discover rumors in social networks, it is necessary to have marked data, which also reflects the importance of humans, so I need to use crowdsourcing platforms in my project. The system introduced in the article is to help people to play a greater role in a system and help people find better ways. I think this is very effective. Enhancing the role of people can undoubtedly increase efficiency. At the same time, I think that this system has also contributed to the subsequent research, not only providing new research ideas, when a field encounters major challenges or bottlenecks, we can consider changing the line of defense to study the problem. At the same time, I think that strengthening the role of people in a system can also better understand the role of people in an application, so that it can better study how to use artificial intelligence to replace humans in computer interaction in the future. In the end, the article also raises a deeper question, should we accept computers help us think, the application of such systems has no intention to raise the workers’ level, and to a large extent can help new hands adapt to a system, starting work more quickly. Such a system can largely allow people control system instead of passively accepting algorithms, so how to define the application direction of artificial intelligence in the future is also a problem that we need to think about.

Question:

  1. Do you think the system mentioned in the paper can help new hands adapt a new system?
  2. Do you think extend people’s ability by computer can help us research the role of people in human and computer interaction?
  3. Should we accept the idea that “computers help people think”, will it lead other problems?

Read More

03-25-2020-Yuhang Liu-“Like Having a Really bad PA”: The Gulf between User Expectation and Experience of Conversational Agents

yuhang Liu 1 Comment

Summary:

The research background of this paper is that many conversational agents are currently emerging. For example, every major technical company has its own conversational agent. As a key mode of human-computer interaction, it has a lot of research significance, so this paper reports the results of interviews with 14 users, and finds that user expectations are very different from the ways of system operations, so the author has finished researching the feedback from these 14 users. The following conclusions were reached:

(a) Change the ways to reveal system intelligence

(b) Reconsidering the interactional promise made by humorous engagement

(c) Considering how best to indicate capability though interaction

(d) Rethinking system feedback and design goals in light of the dominant use case

In general, the functions that the conversation agent can achieve and its impact on human life are still far from people’s expectations. So it is need to be improved better on how people work and their design goals based on their needs.

Reflection:

Then I will talk about my thoughts on these suggestions:

First of all, I very much agree with the author’s suggestion, interactional promise made by humorous engagement. Based on my only interaction experience, I think that humorous interaction methods are very effective in improving user experience and making interaction commitments. I rarely use Siri, but I remember that Siri has a lot of humorous reality, and when asked a specific question, there will be relevant answers. Although this does not help much to solve the problem, it can improve the user experience, and I think that making interactive commitments in this way can also help users better understand the conversation agent, add fun to use, and improvements will make users have confidence in the conversational agent.

Secondly, I think that the other suggestions are mainly regarded as a better demonstration of the ability of conversational agents to users, which is also in line with the central idea of this paper, that is, people’s expectations are far from the goals that the system can achieve. I don’t know the true ability of the system, which leads to the continuous accumulation of disappointment of unfinished tasks, and thus gradually abandon the use of conversational agents. I think I gradually reduced the use of similar products because I thought that the operating systems I wanted to perform were difficult to meet, and in retrospect, I didn’t know what functions the system could really accomplish. So I think it is imperative that users need to really understand the system’s capabilities, use it in a correct and efficient way, and constantly improve their satisfaction in order to realize successful interactions, and then increase the use of conversational agents. At the same time, the emergence of this problem cannot be completely attributed to the user’s wrong use. Technology companies also need to better understand the needs of users, innovate interaction methods, try to change the previous way of conversation communication, broaden interaction methods, and add new features to continue to meet people’s needs.

Question:

  1. What is the role of those conversational agent in your life?
  2. What functions can be added in your mind?
  3. Do you think you don’t know the abilities of these conversational agent clearly?
  4. Do you think it might be useful to design a conversational agent follow the suggestions mentioned in this paper?

Read More

03-25-2020- Yuhang Liu -Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time

yuhang Liu 1 Comment

Summary:

This paper proposes a new system. The system can combine crowdsourcing workers with machine learning to get better chat robots. The motivation for the authors to propose this idea is: fully automatic chat robots usually do not respond as well as crowd-driven conversation assistants, which is also obvious in our lives. But crowd-driven conversation assistants have higher cost and longer response time. So the author built the Evorus system, which is a crowd support conversation assistant. There are three main ways to achieve more efficient:

  1. This new system can integrate other chat robots;
  2. It can reuse previous answers;
  3. It can learn to automatically approve responders;

In short, when users chat with the system, users can evaluate the response, when the response is not ideal, the system can quote the answers from the crowdsourcing workers, and at the same time, it can learn the Q & A, and take the next time to answer the similar questions. In the direction that has been practiced, you can quickly answer questions. This speeds up Q & A, but also improves accuracy.

Reflection:

I believe that in daily life, people will definitely have access to a large number of automated question answering systems. For example, when going to the official website of UPS, there will be a chat robot popping up to ask your purpose, but usually there are only a few directions, However, when people’s requirements tend to be complicated, the chat tends to be complicated, and the automatic answering robot cannot handle it, which will make users go to phone consultation or other homepage. I think this response mainly comes from pre-booked questions and answers, so I think the system proposed by the author has a very important use value.

At the same time, I think that the biggest advantage of this system’s answer through the self-learning crowdsourcing system is that it can be updated continuously in time. Frequent updates usually consume a lot of manpower and resources, and timely updates are more important in communication tools. In network, the terminology and emerging vocabulary are updated very quickly. If it can be updated frequently by studying the accepted answers in each response which need crowdsourcing workers engage, it will have a very positive impact on system maintenance and users.

Finally, the system introduces the answering system into a wider field, not only in the way of updating, revising, and answering questions, but also more importantly, combining humans and machines, and opening a sealing systems to make it can be continuously updated. And more and more innovative projects will be added to it, which is what I think is more meaningful than the system itself.

Question:

  1. Do you think there are any other fields this system can add?
  2. How to evaluate crowdsourcing workers response, in other words how to make sure crowdsourcing workers’ response is better than machine.
  3. What is the difference between the system mentioned in this paper with other Q&A machine in modern society.

Read More