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.
2004年4月14日
2004年4月13日
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.
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.
2004年4月12日
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.
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.
2004年4月11日
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.
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.
2004年4月10日
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.
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.
2004年4月9日
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.
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.
2004年4月8日
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.
订阅：
博文 (Atom)