This afternoon, Mr.Lu gives us a wonderful lecture of WDS in Chinese. He thinks it is good for the new students to understand WSD. And in his lecture, he added some newest cognition of WSD.
At the last I have a short lecture of how to design the net structure in matlab. There are fifteen pieces of experience.
Good! I think. But I find my speech speed is somewhat fast.
2003年11月30日
2003年11月29日
MonthReport and Matlab for NN
When I open my email, I find there is a email from Dr.Tliu. He requires all the month reports of each group.
And some days ago Mr.Lu told me to write some reports for him. So, I prepare to the month report of my works' situation of this month.
I outline my works into four parts: Audio for IRLab, NN_Experiment_of_WSD, CUP-DIC, and WSD_Studying.
When I finish it, I use the technique to build a catalog of my report and convert it into PDF format. I send it to Mr.Lu for his opintion.
When I come here to write my blog, I find a email from Mr.Lu. He requires me to make a short lecture of Matlab for NN. I agree with his requirement and do the ppt at once.
ok.I have prepared for the weekly lecture which turns to WSD group of Mr.Lu.
And some days ago Mr.Lu told me to write some reports for him. So, I prepare to the month report of my works' situation of this month.
I outline my works into four parts: Audio for IRLab, NN_Experiment_of_WSD, CUP-DIC, and WSD_Studying.
When I finish it, I use the technique to build a catalog of my report and convert it into PDF format. I send it to Mr.Lu for his opintion.
When I come here to write my blog, I find a email from Mr.Lu. He requires me to make a short lecture of Matlab for NN. I agree with his requirement and do the ppt at once.
ok.I have prepared for the weekly lecture which turns to WSD group of Mr.Lu.
2003年11月28日
Chat with a good teacher!
At the last class of Soft Engineering, Mrs.Wang Yuying invited two good teacher who,with many years developing experience in software company, had returned back from American.
After the class I got the email address and msn address of one of the two good teacher. The teacher is ebullient and help a lot to my Software Engineering and my project of MSCVB.
Yesterday, she suggested me to study for her class Object Oriented with UML. And this evening I went to listen to her class. She had prepared enough for all of us. She made a Wame-up-session for her class. Her English is very good. She prepared to teach us in fully English on class. I think this way is very good for me to practise my listening English.
And my msn have conteced to hers. We had talked in English for several times. This evening our talking subject was why her outlook express can not send email.
Thanks a lot to this ebullient and good teacher.
After the class I got the email address and msn address of one of the two good teacher. The teacher is ebullient and help a lot to my Software Engineering and my project of MSCVB.
Yesterday, she suggested me to study for her class Object Oriented with UML. And this evening I went to listen to her class. She had prepared enough for all of us. She made a Wame-up-session for her class. Her English is very good. She prepared to teach us in fully English on class. I think this way is very good for me to practise my listening English.
And my msn have conteced to hers. We had talked in English for several times. This evening our talking subject was why her outlook express can not send email.
Thanks a lot to this ebullient and good teacher.
2003年11月27日
Make headway in WSD
Today, I have some good news to note.
The experiment of the NN-WSD has made sure the input information format. After Mr.Lu and me discussed many times, we have decide a new information from the 50M corpus. And Mr.Lu has programmed for it. My designed NN-WSD model has been made sure by us. So, our experiment will run out the first conclusion soon.
I have mad a study plan in WSD that I should read a paper every day. After the repairment of my computer's operating system, I realized it today.
I have read a paper by a graduate student from Da Lian University of Technology. This paper includes some good idea for WSD. The auther had defined a dynamic context window to adapt for the process of WSD, and there was a filter to filtrate the inessential word in the context for the multivocal word.
There is a good idea for NLP is that we can make sure some base normative corpus for a experiment and then we use the normative corpus to find the other normative corpus in large-scaled corpa.
Ok.I must go for MCM class now.
The experiment of the NN-WSD has made sure the input information format. After Mr.Lu and me discussed many times, we have decide a new information from the 50M corpus. And Mr.Lu has programmed for it. My designed NN-WSD model has been made sure by us. So, our experiment will run out the first conclusion soon.
I have mad a study plan in WSD that I should read a paper every day. After the repairment of my computer's operating system, I realized it today.
I have read a paper by a graduate student from Da Lian University of Technology. This paper includes some good idea for WSD. The auther had defined a dynamic context window to adapt for the process of WSD, and there was a filter to filtrate the inessential word in the context for the multivocal word.
There is a good idea for NLP is that we can make sure some base normative corpus for a experiment and then we use the normative corpus to find the other normative corpus in large-scaled corpa.
Ok.I must go for MCM class now.
2003年11月26日
New Operating System
Yesterday, I spent nearly a whole day to change my Operating System.
But at last, there was no spare space in C dick. So I must to install the Operating System again at another disk.
This morning, I formated my D disk with near 13 G. And then I installed every software.
During the installing, I clean up all my documents.
Right now, the installment has been finished and I change my desktop theme.The new theme is cool.
Good tool is the good foundation of my other work. And I will do my best from now on!
But at last, there was no spare space in C dick. So I must to install the Operating System again at another disk.
This morning, I formated my D disk with near 13 G. And then I installed every software.
During the installing, I clean up all my documents.
Right now, the installment has been finished and I change my desktop theme.The new theme is cool.
Good tool is the good foundation of my other work. And I will do my best from now on!
2003年11月24日
Some good news
This evening, we have a exam for the Communist Party college exam. After the exam I goto join the summarizable meeting of the CUMCM of 2003. At last, YU qiyue, Hongweijun and I form a team for the 2004's MCM. It is a good news for me.
After the meeting, I and Victor goto join the lecture of a people with successful carve out. The speaker says we should keep going ahead every day, and we should stick to the thing we devote to and never to abandon easily.
Indeed, I think so.
After the meeting, I and Victor goto join the lecture of a people with successful carve out. The speaker says we should keep going ahead every day, and we should stick to the thing we devote to and never to abandon easily.
Indeed, I think so.
2003年11月23日
2003年11月21日
2003年11月17日
more tasks
I listed my recent tasks. And I was frightened by the table. There were eight big tasks I should do.
And I made a full plan to complete them, I discover that I must be very busy during this week.
Ok. I should began to complete the first one.
And I made a full plan to complete them, I discover that I must be very busy during this week.
Ok. I should began to complete the first one.
2003年11月16日
Ulread Video Studio
Ulread Video Studio is very powerful for editing and generating video files, such as avi and mepg format.
This afternoon, Dr.Tliu gave me the scenario for IRLab's intruduction. After had supper, I began to use Ulread Video Studio to complete it.
Ulread Video Studio is very interesting. You can merge video snippets, pictures, audio snippets, and texts to a nice and abundent video file.
Just now, I have constructed the whole frame. Tomorrow, I will photo some pictures to insert into this frame, the day after tomorrow I can invite Zsq and Wanglijuan to dub, and spending some time to modify it I can do a very good video to introduce our lab.
It is a good work.
This afternoon, Dr.Tliu gave me the scenario for IRLab's intruduction. After had supper, I began to use Ulread Video Studio to complete it.
Ulread Video Studio is very interesting. You can merge video snippets, pictures, audio snippets, and texts to a nice and abundent video file.
Just now, I have constructed the whole frame. Tomorrow, I will photo some pictures to insert into this frame, the day after tomorrow I can invite Zsq and Wanglijuan to dub, and spending some time to modify it I can do a very good video to introduce our lab.
It is a good work.
2003年11月15日
2003年11月14日
project manage
Project manage is very interesting and diffucult.
The tools for project manage are many, for example Microsoft Project Manager .
The Gannt Graph and the Pert Graph are two kinds of project manage graph.
Constructing a Pert Graph is trobulesome.
And so on……
The tools for project manage are many, for example Microsoft Project Manager .
The Gannt Graph and the Pert Graph are two kinds of project manage graph.
Constructing a Pert Graph is trobulesome.
And so on……
2003年11月13日
2003年11月12日
An experiment scheme
This morning, I came to 610 and discussed an experiment for WSD with Mr.Lzm. And we had some different view on experiment. But we made sure the scheme at last.
The whole scheme had been made.
The whole scheme had been made.
2003年11月11日
WSD and dictionary groups' progress
This morning, I discussed with Mr.Lzm for WSD and dictionary groups' work.
I listed all the problems and tasks of the two groups. We discussed the way to construct the third layer and the fourth layer. And we discussed the way to do experment of WSD.
There were good progess.
We will go on discussing tommorw.
I listed all the problems and tasks of the two groups. We discussed the way to construct the third layer and the fourth layer. And we discussed the way to do experment of WSD.
There were good progess.
We will go on discussing tommorw.
2003年11月10日
yesterday's busy!
This diary should be written yesterday. But yesterday I left from a Mathematics department office at 23:30. Because our teaching evaluation project's all algorithm modules must be modified.
And we, three students, began to modify all modules and test one by one. After we tested the last module, it was 23:30. And we were all tired.
During the testing, we found a strange phenomenon that when we tested whether two same long type number were equal, the system's answers was difference at random. We were puzzled by this problem firstly. At last, we found that when we compare whether two long type number are equal, we should not use "=" directly, and we can use the absolute value of a minus b less than a infinitesimal number. This was the effictive solving means.
Today, Monday, a usually busy day again.
Tommow I will discuss some problem with Mr. Lzm.
And we, three students, began to modify all modules and test one by one. After we tested the last module, it was 23:30. And we were all tired.
During the testing, we found a strange phenomenon that when we tested whether two same long type number were equal, the system's answers was difference at random. We were puzzled by this problem firstly. At last, we found that when we compare whether two long type number are equal, we should not use "=" directly, and we can use the absolute value of a minus b less than a infinitesimal number. This was the effictive solving means.
Today, Monday, a usually busy day again.
Tommow I will discuss some problem with Mr. Lzm.
2003年11月8日
Two astonishment
Yesterday night I found a nice paper about neural network used for word sense disambugation. But I did not read it over. This morning, when I did today's work scheme, I decided to read the paper firstly.
The idea of this paper is very nice, I think!
Through the context vector, we could build a lot of input models and output models, then train the network to get the optimal structure. Later we could input the openning testing corpus, simulated to get the results.
The idea is nice.
Just now I searched "灰色" in Super Star. And I got a book with a string "grey" on the cover. At the first glance, I thought it was wrong, as I thought it should be said "gray". In order to make sure the answer, I found "gray" and "grey" in a dictionary. The answer was that they are same but "grey system" usually to translate for "灰色系统". Had found this true, I searched the "grey system" in Internet. Wa! The returned answers were more related to "灰色系统" than "gray system".
I got the conclusion that when you needed to translate a English word to Chinese or Chinese word to English, you'd better search more and more detailed, or ask for other person.
The idea of this paper is very nice, I think!
Through the context vector, we could build a lot of input models and output models, then train the network to get the optimal structure. Later we could input the openning testing corpus, simulated to get the results.
The idea is nice.
Just now I searched "灰色" in Super Star. And I got a book with a string "grey" on the cover. At the first glance, I thought it was wrong, as I thought it should be said "gray". In order to make sure the answer, I found "gray" and "grey" in a dictionary. The answer was that they are same but "grey system" usually to translate for "灰色系统". Had found this true, I searched the "grey system" in Internet. Wa! The returned answers were more related to "灰色系统" than "gray system".
I got the conclusion that when you needed to translate a English word to Chinese or Chinese word to English, you'd better search more and more detailed, or ask for other person.
2003年11月7日
WSD for research
This afternoon, when Mr.LZM came to 615 to read Journal of Harbin Institute of Technonoly(New Series) we talked much on the reserach on WSD. He told me there were a lot of reseraching points inWSD. And we discussed a lot of techniques which could be used for WSD,such as neural network, heredity arithmetic, Simulated Annealing Algorithm, Gray system, and so on. Firstly, we didn't know whether neural notwork had been used in WDS. After we searched in Internet, we found that neural network had been used at early 90's aboard, and at 2001 domesticly. So I thought it is a good way for WSD. And the other ways were also good for try.
There were so much could be researched on.
There were so much could be researched on.
2003年11月6日
A very busy day！
It is true that this is a very busy day!
This morning we went to a whole morning's classes of VC++ and Soft Engineering. At 13:00, I went to visit harbin electric machinery factory. It is true that the factory is famous and of large scale. At 15:30, I came back to lab and do my work again. At 18:30, I went to join a check for a software that we have spent more than half a year. And the result was that we should modify nearly half of the evaluation algorithm modules.
Right now I must complete the soft engineer's study.
So busy……
This morning we went to a whole morning's classes of VC++ and Soft Engineering. At 13:00, I went to visit harbin electric machinery factory. It is true that the factory is famous and of large scale. At 15:30, I came back to lab and do my work again. At 18:30, I went to join a check for a software that we have spent more than half a year. And the result was that we should modify nearly half of the evaluation algorithm modules.
Right now I must complete the soft engineer's study.
So busy……
2003年11月5日
the Notice for Transfering Deliver Paper
This afternoon I received the notice for transfering deliver paper from the Editorial Department of CONTROL AND DECISION. They told me that as there are too many papers to publish and the publishing period had been delayed and so the employing proportion of new papers was too low and my paper had not been employed. But they proposed me to transfering deliver the paper to the 2004 annual learing meeting of the control and decision and if I agree with it they would deliver it to the annual meeting directly and the annual meeting would employ the paper preferentially.
Later I found some information relating to the annual meeting. And I found that the meeting is one of the six authoritative learning meeting in China. And the meeting includes the areas which gray systems included. The meeting's organizers are six big organization.
I introduced the situation to Dr.Liu and Dr.Su. Dr.Liu suggested me not deliver the paper to the annual meeting and modify the paper again and deliver it to another periodical. Dr.Su suggested me deliver it to Hit periodical.
I have thought it for several hours and there is no conclusion.
Later I found some information relating to the annual meeting. And I found that the meeting is one of the six authoritative learning meeting in China. And the meeting includes the areas which gray systems included. The meeting's organizers are six big organization.
I introduced the situation to Dr.Liu and Dr.Su. Dr.Liu suggested me not deliver the paper to the annual meeting and modify the paper again and deliver it to another periodical. Dr.Su suggested me deliver it to Hit periodical.
I have thought it for several hours and there is no conclusion.
2003年11月4日
design error
This morning, I meet Mr.Tliu at 615. After I started my computer, he told me there were a lot of design error in my program for the dictionary. And I started my program, he analysised some errors in the program, and gave me many constructive advices.
After the examing of the program I use a famous dictionary's program, and I found some other errors in my program.
Why there were so many errors? I think there were two reasons.
Firstly, when I was programing for it, I wanted to complete a primary version, and then to keep consummating it. And this is a good working model for me right now, I think.
Secondly, although I have completed a lots of small projets before I joined in IR, I have a lot of flaws in programing. I should improve it. Right now, we are studying Soft Engineering, I want to study it well firstly.
After the examing of the program I use a famous dictionary's program, and I found some other errors in my program.
Why there were so many errors? I think there were two reasons.
Firstly, when I was programing for it, I wanted to complete a primary version, and then to keep consummating it. And this is a good working model for me right now, I think.
Secondly, although I have completed a lots of small projets before I joined in IR, I have a lot of flaws in programing. I should improve it. Right now, we are studying Soft Engineering, I want to study it well firstly.
2003年11月3日
WSD's idea
At this noon, I studied for a paper which was written by Changling Huang. In this paper, there is a good idea for WSD. Usually, we do WSD by making choice of the number of the semantic classes. But we do not make very good language model for the words in the context. And in this paper, the context is fully used to construct the language model. There is a noun named observational window for every word. Make a statics of probability for the words in the window to the key word, and build a vector for the key word of the context. If you make the vectors for all words, you can get a vector space. Then choice some typical high-frequency words to imply the clustering algorithm to get a lot of sets of words.
In this paper, there is a conclusion that using this method for a large corpus, you can get a lot of semantic sets which is consistent with Cilin at average probability of 81%.
This is a very good idea for WSD. But I think there are lots of other good method for WSD. We should mine them.
In this paper, there is a conclusion that using this method for a large corpus, you can get a lot of semantic sets which is consistent with Cilin at average probability of 81%.
This is a very good idea for WSD. But I think there are lots of other good method for WSD. We should mine them.
2003年11月2日
编程任务完成
最近两日都在完成词典界面的设计任务，卢老师交给我的任务是采用较好的界面提供词典第五、四、三层的查找功能，要求使用vb实现，原因是可以快一些实现该任务。
参考了一些有名的词典后我决定采用treeview控件来实现第五层的查找功能。但是treeview控件我从来没有用过。 又一次采用摸着石头过河的思路，我逐一解决了各个难点。最后实现的界面的第一版。 稍候又将第四层和第三层的信息加入，昨天上午最后完成了final版。 今天中午给卢老师看看后，各项要求都已经实现了。
VB真的很强大，我算是体会到了。
今天又花了一些时间来学习一些VB编程经验。感觉很有成就感呀。
参考了一些有名的词典后我决定采用treeview控件来实现第五层的查找功能。但是treeview控件我从来没有用过。 又一次采用摸着石头过河的思路，我逐一解决了各个难点。最后实现的界面的第一版。 稍候又将第四层和第三层的信息加入，昨天上午最后完成了final版。 今天中午给卢老师看看后，各项要求都已经实现了。
VB真的很强大，我算是体会到了。
今天又花了一些时间来学习一些VB编程经验。感觉很有成就感呀。