May day holiday's plan

This is the last festival of our seniors.

So many things I should do. Tomorrow I wish to watch the best TV 《大染坊》. It is so nice that my dormmates had watched two times. And May two, there is a table tennis game of our lab. After two days relax, I should complete my tasks. They are so many, but I believe I can finish them.

Tired & Excited

This morning, when we came back from Erlong Mountain, all of us were tired and excited.

The trip of Erlong Mountain

This is a very nice day. Yes, I think so.

It was 6:00 when some of us get up to go shopping for some meat, vegetable, fish. All of us, including about 25 people, went for Erlong Mountain at 10:00.

Erlong mountain is beautiful, although not good as Mount. Emei, with two little big mountains and a lake. After a simple breakfast or lunch, we began to visit the scenery. Firstly, we went to the lakeside and then the Wanfo Temple by boat. There were lots of josses in the Wangfo palace, maybe thousands.

The more interesting thing was our mountain climbing. All of us were excited. LEE first went to the top of the mountain. Dr.Tliu went to the top with a little big branch. We agreed with that the branch was so heavy that Dr.Tliu climbed little slowly. At the top, we could look the beauty spot like bird's eyes. So beautiful that we felt our breadth of mind widened a lot.

When we came back to our casualresidency, ten of us found a basketball playground for a football game. Such a wonderful game that the final score was six to five.

Another exciting thing was preparing for supper. Mr.Lzm made and guided us to finish lots of dilicious dishes. My task was to dissect the four fish and make a poached sliced meat with vegetable and spices. And after my reminiscence, I made three dishes of it. When we had our supper, I thought it little delicious.

So tired a day, and we were going sleep with good mood.

Survey of Erlong Mountain

Tomorrow, we will go to Erlong Mountain, so we should make a simple survey.

This morning I, with CiH and his girlfriend, went to Erlong Mountain for a simple survey. We went there by three buses. And after a simple comparision we chose a best rest house.

After we came back, lots of us began to arrange detailed.

May a good enjoyment to us.

Successful people and personal traits

This week our English class's topic is successful people and personal traits.

And we discussed lots of successful person, such as Mao Ze dong, Tom Hanks, Bill Gates, Michael Jordan, George washington, and so on. And after our investigation about their personal traits, we agreed with that there were some common behavior traits of highly successful people.

They are as follows:
1. They are hard working.
2. They are honest.
3. They persevere.
4. They are friendly.
5. They are lifelong learners.
6. They over-deliver.
7. They seek solutions in the face of problems.

So many personal traits.

The most busy week

I had spent this week, the most busy week with me.

So many tasks, so many papers, so much knowledge, and so much harvest for me.

This morning I finished my last task of this week, the presentation for coreference resolution. The content of this paper was so much to me to finish it in fifteen minutes. When I finished it, Dr.Tliu gave me some advice to me. He thought my voice speed was so fast that many listeners could not understand this paper. I also found out this flaw to me.

I must correct it. Slower voice speed will better.

Coreference Resolution Paper

There was a paper of IJCNLP 2004 related to Coreference Resolution that was turned to me. And tommorw morning I will make the presentation about this paper. After four times I had read this paper and the related papers, I could understand the essence.

There were three main methods for Noun Phrase Coreference Resolution. They are String matching scheme, Name alias and Apposition. And this paper's main idea was based on Soon et al., 2003. It collected more string features about the candidate antecesstor and its anaphor. Then employing C5.0 Decision Tree Algorithm, the anaphorial relationship between the Noun Phrases could be made sure.

As discribed in this paper, Decision Tree algorithm has been used a lot for Coreference Resolution. And there are more importance of coreference resolution for IE and Auto Summarization.

There are so many papers for me to read.

During the recent papers preparing powerpoint, I found out that I could understand the papers more deeper. It is a so good manner for me to read any good papers.

This evening's papers review meeting

This evening, the crew of our lab went on discussing the papers of IJCNLP 2004.

There were seven students to give their presentations. But before the meeting, there were something wrong with the projective machine. So Dr.Tliu gave us the advice about how to prepare for the presentation.

Originally Dr.Tliu gave each of us fifteen minutes to interpretate the paper. However, when we finished our presentations it was nearly to 21:30. I felt the information of this meeting was very dense. And we should understand the papers for a long time.

This weekend I have to prepare for the last paper about co-reference resolution.
Good chance to me. Try again!!

The Shawshank Redemption

The Shawshank Redemption is named as one of the ten most significative films for any human being.

And there were some actor's lines impact me a lot. I shared them to you:

Fear can hold you prisoner. Hope can set you free.

It takes a strong man to save himself, and a great man to save another.

Remember, Hope is a good thing, maybe the best of things and no good thing ever dies!

Get busy living, Or get busy dying.


And I thought it's a true best film that was so valuable to be tasted once again and again.

IE for summarization

How can IE supply for Auto-Summarization? This is one of the IE big questions for me this week.

Fortunally there were some persons had researched and got good achievement on it. It was included in a paper which was named as Information Extraction and Summarization: Domain Indepence through Focus Types. The authers were of Department of Computer Science, Columbia University. Although it was written at April 2, 1999, I thought it was very newly for me. As said in this paper, IE could supply for Auto-Summarization. Likely to the common outline, to a original article, IE found out the name entities, the relationship between the name entities and filled some templates to the type of the common articles. Finally, the sentences which contained the most improtant information, would be chosen to combine a summary. In order to get more coherent summary, the final step was to change the order of the sentences. That is, the sentences' order of the summary would be not the same as that of the original article.

The idea is very fit for our recent demand. I think so.

IE big questions!!

There were seven IE big questions for our investigation task this week. And each of them had lot of related materials. So the answers for these questions were hard to found out.

But I had got some wonderful websites about IE. Originally there was a nice conference named as MUC(Message Understanding Conference) whose main point was about IE. And there were lots of famous IE systems.

During the survey, I found out that Coreference Resolution was very important for IE. As based on anapgora resolution there were more relations can be mined out.

So wonderful research point is AR(or CR) :)

Congratulations to the No.1 Experimental Satellite

Congratulations to the No.1 Experimental Satellite. It is our university's proud.

The speech of our lab

At the lab meeting, I didnot make the oral English speech. Because I had thought that if I did the oral English speech, maybe I could not express well and many audience would not understand my viewpoints.

I would try to practise more and use the simplest words to express my viewpoints.

By Mjs's speech, I indeed found out the very importance of English study. And I shoud insist on writing English diary.

And Mjs gave us his impression of the IJCNLP 2004.

He mentioned the First ACL Lifetime Achievement Award's winner Prof. Aravind Joshi. He has contributed a lot on anaphora resolution.

It is very good news for me to improve my interesting on this topic.

Prepare for tomorrow's speech.

Tomorrow morning, I will give two speech, search and causal relation extraction. But I have not prepared for the speech of search.

So today for me is very busy.

Before some days I had read the paper many times and I had written the paper review outline. But when I was doing the ppt for this paper, I found out that I must read this paper for more times.

Right now I began to understand the old sentence that you will fully understand the book after you have read it 100 times.

The English presentation

These two weeks our lab will hold two meetings to analyze and understand the papers that were brought by Mjs from Hainan Conference.

And there were three papers to me. Originally I planed to make my presentations at next week. But as there were few person to make their presentations this week and I had read two of them, so it was my trun to make two papers presentation this weekend.

This time, Dr.Tliu demanded English powerpoint and oral English. So we must study the papers deeper and deeper. This evening, I prepared the presentation for the paper of Causal relation extraction. Causal relation was so important for the Question-Answer system. As it performed very lower accuracy in recent QA systems.

Based on the experimence of my pure English presentation about high-tech of our English class, I had done the powerpoint and imagined the report scenes at the meeting.

Simply told me that it was a very good chance for me to make the pure English presentation and I should treasure this chance. Thanks for Simply's encouragement.

The difference between men and women

We were discussing the difference between men and women in the English class at this afternoon.

What is the difference between men and women? Our teacher gave us six main aspects: friendship, stress, selflessness, and so on.

We discussed them drasticly.

Oh, the administrators of this building has come now. I must go. I will go on this topic after some days.

Anaphora resolution's methods

There were lots of methods for anaphora resolution. As described in Dr.Wang Houfeng's survey paper, there were some theoretical methods such as, Hobbs Algorothm 1997, Center Theory of Grosz & Sidner 1983. But they had not been used directly.

The classical techniques of this topic were two main aspects.
The first was based on syntax. There were so many method on it, such as RAP of Lappin & Leass in 1994, Kennedy & Boguraev in 1996, Mitkov in 1998.
The another was based on corpora. For example, there were some methods like Simple Co-appear, statistical method, Design tree, clustering and Memory based Learning.

When I read this survey paper, I bethought of that based on the syntax parser we can make good anaphora resolution. But when I asked Mjs. He told me that right now, we can not realize the syntax component analysis. If I give a sentence to the parser, I can not get the subject, object, and so on.

It seems difficult of this topic. I should read more papers on it.

Anaphora resolution

Beginning at today, I have my fully task for my graduating design. I am assigned to the research point of Anaphora Resoluation.

At this time, I changed my usual way for research. I could read some linguistic papers on this topic, then some survey in Chinese, then some useful application in Chinese, then some survey in English, then some application in English. I thought after this order, I could understand it very quickly and efficiently.

This afernoon, I, at our campus library, studied the first lingustic paper of Anaphora resolution. Ok. It was great.

Keep on this order.

Men and Women

This week our English class's topic is Men and Women. And there were lots of funny sentences of our class:

SUCCESS:

A successful man is one who makes more money than his wife can spend.

A successful woman is one who can find such a man.

STYLE:

Men wake up as good-looking as they went to bed.

Women somehow deteriorate during the night.

MONEY MANAGEMENT:

A man is a person who will pay two dollars for a one dollar item he wants.

A woman will pay one dollar for a two dollar item that she doesn't want.

HAPPINESS:

To be happy with a man you must understand him a lot and love him a little.

To be happy with a woman you must love her a lot and not try to understand her at all.

MARRIAGE EXPECTATIONS:

A woman marries a man expecting he will change, but he doesn't.

A man marries a woman expecting that she won't change and she does.

MARRIAGE DECISIONS:

Men marry because they are tired.

Women marry because they are curious.

Both are disappointed.

MARRIAGE AND THE FUTURE:

A woman worries about the future until she gets a husband,

A man never worries about the future until he gets a wife.

MEMORIES:

A woman will always cherish the memory of the man who wanted to marry her.

A man cherishes the memory of the woman who he didn't marry.

UNDERSTANDING WOMEN:

There are two times when a man doesn't understand a woman - before marriage and after marriage.

WHAT A WOMAN WANTS:

Only two things are necessary to keep one's wife happy...

- One is to let her think she is having her own way.

- The other is to let her have it.

LONGEVITY:

Married men live longer than single men, but married men are a lot more willing to die.

MISTAKES:

Any married man should forget his mistakes - no use two people remembering the same thing.

THE BATTLE:

A woman always has the last word in any argument.

Anything a man says after that is the beginning of a new argument.

Nice speeches in YOCSEF

This morning, I joined in YOCSEF. I thought I was very lucky. Because I heard the two high level speeches.

The topic about this YOCSEF Forum was about Human bio-information security. The invited two speakers were Dr.Zhang Dapeng and Dr.Niu Muxia.

Dr.Zhang gave us a very detailed introduction about Biometric Authentication. In his introduction I found that our technoloyu society need more innovation. As there were many many newly modes of biometric. For example somebody thought they could recognize people by the lip lines.

Dr.Niu Muxia's research was full with innovation that he combined hominine immunity system and the computer network system to a newly information security network system. He thought we could extraction our bio-information to be some personnal information, then embed them to the identity card. Doing that we could combine the personal bio-information with the personal identiti card that is the common certification for person. Such a wonderful idea I thought it is.

Innovation is very important for our research. But it is based on very deeply accumulation of all kinds of knowledge.

Playing Table tennis

These days it were very sunny! And all people would be in very good mood. So these days I was in my sports season.

This morinng, I went to the library, and I found lots of good books for me to read. Many books were ralated to AI, GA, Information security, Programing, and data mining. Indeed I found that I should go to look around the books of library. As there were a lot of good books for me.

But when it came to one o'clock this afternoon, I wanted very much to play table tennis. When I returned to my dorm, I met Ma Ning, who had invited me many times to play table tennis. I, with him, played pable tennis up to 3 o'clock. Finally he gave me lots of suggestions to my actions. I thought he was right.

How to make survey?

This afternoon we hold a discussion about our survey conclusion. There were some exciting survey conclusiones that Zsq and Chen Yihen gave us a whole architecture view of their IF system. The classical algorithm ANN and GA could be used in their system. It seemed that our lab will pay more attention on all kinds of machine learning algorithms.

And our group, Mrs.Qin, Benz and me, gave our survy conclusion. My task in this week was to investigate the related materials about semantic web and XML. I thought that semantic web and XML were both big topics for my only one week's survy. There were very very much more topics about them. I found out that lots of their applications were relevant to each other. Dr.Tliu had given us a hint about how to utilize XML and semantic web for NLP. And after a simple search by google, I found out that there were three times workshos about NLPXML. This workshop's main subject is that NLP should be able to provide XML with the answer to resolve the "point of the creative bottleneck", and XML should be able to provide NLP with deeper semantic structure clues.

The problem of our survey was discribled as that we had not be very clearly about how to make survey. So I should first make sure how to make better survey.

It is complicated

One of my recent papers that I should read was very complicated. Its name is Categorizig Unkown Text Patterns for Information Extraction Using a Search Result Mining Approach. There were some misleading points that I could not understand them very deep. For example, there was an unexpected appearing mathematical formula S: the set of seed instance. I guessed that I should understand it after a while.

This exercise day!~~!

Life lies on sports. This is an old adage. And I did as it today.

This morning, when it was nearly 10:00, I felt little tired. I walked out to the exercise ground beside our Integrated Building. I did some action on the parallel bars and horizontal bar and did some leg block. After I finished them I felt some comfortable.

This noon, I, with simply, played table tennis for nearly one and a half hours. Simply played table tennis very smart. She played very well. And there were lot of nice catches of her. She liked to kick the ball to the directly right side extraordinarily. So good table tennis player she is.

I would like to do lot of exercises these days.

Simple survey of Semantic Web

One of recent task is to survey of semantic web. Formally I found a specialized website of semantic web.

This afternoon, I began to visit this website. At beginning, I had thought semantic was a very little area of web intelligent information processing. However, after I had read some web pages about it, I found out that semantic was a very, very large research area. And it was so rising and hot that there were just only two times special international conferences hold for it in recent two years.

Semantic web could be thought as the second generation of our internet web. As it said from the creater Tim Berners-Lee that the first generation of intyernet, that based on HTML, is only for human-beings, and the machines could not understand them. And he was trying to overthrow himself to creat the second generation which was generally seemed as Semantic web. With lots of tages Semantic web could be understood by the machines. And lots of application on semantic Web can bring us lots of convenience.

So powerful newly thing.

Our play&Our teacher

This afternoon, all of my classmates and our teacher watched the five plays of us. It was very funly for us to play. And all of us had tried our best to prepare for the plays.

Among the five plays, I thought group two was the best one. Their actors' lines were very practiced and there scenes were very ample. We all enjoied ourselves at this afternoon. And there were lots of pictures which we could memorialize them.

And after the class, our teacher invited six of us by sortition to dinner with her. And we went to a far restaurant that sells only maigre food. We all had a fully maigre supper tonight. During the dinner time, we talked lot about our teacher's abroad study life.

our teacher was a Buddhist. And she told us lots about Buddhism. After nearly three hours talk with our teacher, we had learned a lot about the Buddhism.

Our teacher was so good a woman. We all likes her.

Prepare for our play!!

Tomorrow afternoon's English class, we will have our play. And our play's name in Chinese is 鹿鼎记. And I was dicided to be the role of Bob, whose name in Chinese is 韦小宝. And we had dried run three times. This evening, we prepared for it again.

We found out that the biggest problem for us to the play was we could not rember all the actor's lines. So we must pay more time to practise it.

Why so tired?

The recent two days' evening, I was not in lab. Instead I was in the classroom of Building A.

But when I had read for about half an hour, I was very sleepy. I must have a snap nearly for about an hour. And after I awaked, I felt some tired. After a face-wash, I could go on my studying.

Today I found some information about health, bite and sup, rest, and taking exercise. It was bad to be front of computer for two hours without any rest. Maybe I had adapted to be front of computer in evening. When I was studying in classroom in evening, I would feel tired.

Maybe, the basis reson was there was not enough exercise to me these days.

Chaotic intelligent information processing

Right now I could make sure that Chaos theory can be used in the information processing area.

This afternoon, I read summarize about Chaos and intelligent information processing. The application of chaos in information processing has been drawn more and more attention of the researchers. A large amount of scientific achievement has been achieved. In this paper, they have reviewed the recently research trends about how to realize the intelligent information processing and apply the intelligent comutation with chaos. I have found out some newly algorithms about the present hot algorithm, such as chaotic GA, chaotic ANN. They are great. However, there is not any real applicatin about them in this paper.

So chaos is very interesting. Last night, I saw a mathematical expression. That is x(n+1)=u*x(n)*(1-x(n)). Somebody said that there was some chaotic phenomena if we increase the parameter u from 0.1 to 4. When u is up to 3.5 even 4, the sequence of x will not be under any rule. And I programed it this morning, and check this conclusion out. My test conclusion was same as the forementioned one.

Great!

Chaos and NLP

These days I was thinking a problem that whether Chaos theory is related to NLP.

Because chaos is a state relate close to the system's initial state. And Chaos discribes some system of disordered. Maybe it is related to NLP.

It is difficult to me. I must think it for long.