I had not swum for three years. During my undergraduate life, I only swam three times when I was in the course of P.E. When I was a child in my hometown， I liked swimming a lot. Each summer vocation, we all guys went to reservoirs, rivers and swimming pools.
This afternoon, Caizhi Zhu, one VS of MSRA invited us to Sunshine Swimming Pool. It was very nice feeling of swimming. I believed so. In the morning, Chengjie Sun and I went to Wall-Market for shopping some swimming pants, hats and glasses. Afternoon lunch, we seven guys went to the pool. Carl, Xiaoguang Hu liked swimming very much. And they were in advanced level. They joined us.
We had our swimming from 14:30 to 17:30. Without any professional coaching, my swimming technique was poor. Luckily Xiaoguang was professional now. And his guide was effective. Chengjie Sun, Caizhi Zhu and I were guided by him on breast stroke. To my original level on breast stroke, I could swim with my head above the surface. I was unable to dive and float out for breathing. Xiaoguang corrected my leg poise and taught me for expiration under surface and inspiration above surface. Based on the two hints, I practiced many times. And finally I was familiar with breast stroke little. I needed more practices.
It was effective for practice and keep health by swimming. I'd like to swim again in next weekend.
2005年8月6日
[Collection]学习英语的六个窍门
当我们意识到有必要学会英语，并且下决心去攻克这个难关时，我们就一定要：
1、投资我们的时间和心智。我们并不傻，有足够的智慧和大脑空间来消化储存那些ABCD。别人能学会，我们也能学会，只要我们善于投资自己的时间。上帝赋于我们每日24小时，上班8小时，睡觉7小时，三餐饭2小时，莫名其妙kill2小时，无论如何应有1小时来学习。越忙的人，越有时间做事；越闲越懒散的人，越找不到时间来做事。
2、要从心底滋生出一种对英语的喜爱之情。把学英语当成一个开心而愉快的美差，而不是硬着头皮、头悬梁、锥刺骨的苦力。因此，先要从简单的入手，找一本好教材或一本故事书（生词量不超过30%）悉心研读，默识揣摸，就会有收获感，尝到甜头，进而信心更足，如开始就啃一本词汇量太大，没有词典看不下去的书，只会扼杀学习兴趣，降低情绪，最终放弃。
3、要有自我约束力，且称之为“心力”吧。春来不是读书天，夏日炎炎正好眠，秋来蚊虫冬又冷，背起书包待明年。总有一些理由不学习。这样下去，我们的英语之树永远长不大。古人云：“人静而后安，安而能后定，定而能后慧，慧而能后悟，悟而能后得。”很有道理。在四川大足佛教石刻艺术中，有一组大型佛雕《牧牛图》，描绘了一个牧童和牛由斗争、对抗到逐渐融合、协调，最后合而为一的故事。佛祖说：“人的心魔难伏，就象牛一样，私心杂念太多太多；修行者就要象牧童，修炼他们，驯服他们，以完美自已的人生。”我们学英语也一样，要能够驯服那些影响我们学习的大牛、小牛，抵制各种诱惑，集中精力，专心学习。
4、要有信心。英语不过是表达思想的一种工具、一种说话习惯而已。我们要坚信，只要有投入，有付出，就会有收获。绝不会“付出的爱收不回。”
5、要有实际行动。一个真正的马拉松运动员绝不会空等奥林匹克金牌从天下掉下来，现在就行动起来。
6、要有连续性、持续性。学英语是一个漫长的过程，走走停停便难有成就。比如烧开水，在烧到80度时停下来，等水冷了又烧，没烧开又停，如此周而复始，又费精力又费电，很难喝到水。学英语要一鼓作气。天天坚持，在完全忘记之前及时复习、加深印象，如此反复，直至形成永久性记忆。如果等到忘记了再来复习，就象又学新知识一样，那么，我们就永远是初学者，虽然在辛辛苦苦地烧开水，却难品味到其甘润。
1、投资我们的时间和心智。我们并不傻，有足够的智慧和大脑空间来消化储存那些ABCD。别人能学会，我们也能学会，只要我们善于投资自己的时间。上帝赋于我们每日24小时，上班8小时，睡觉7小时，三餐饭2小时，莫名其妙kill2小时，无论如何应有1小时来学习。越忙的人，越有时间做事；越闲越懒散的人，越找不到时间来做事。
2、要从心底滋生出一种对英语的喜爱之情。把学英语当成一个开心而愉快的美差，而不是硬着头皮、头悬梁、锥刺骨的苦力。因此，先要从简单的入手，找一本好教材或一本故事书（生词量不超过30%）悉心研读，默识揣摸，就会有收获感，尝到甜头，进而信心更足，如开始就啃一本词汇量太大，没有词典看不下去的书，只会扼杀学习兴趣，降低情绪，最终放弃。
3、要有自我约束力，且称之为“心力”吧。春来不是读书天，夏日炎炎正好眠，秋来蚊虫冬又冷，背起书包待明年。总有一些理由不学习。这样下去，我们的英语之树永远长不大。古人云：“人静而后安，安而能后定，定而能后慧，慧而能后悟，悟而能后得。”很有道理。在四川大足佛教石刻艺术中，有一组大型佛雕《牧牛图》，描绘了一个牧童和牛由斗争、对抗到逐渐融合、协调，最后合而为一的故事。佛祖说：“人的心魔难伏，就象牛一样，私心杂念太多太多；修行者就要象牧童，修炼他们，驯服他们，以完美自已的人生。”我们学英语也一样，要能够驯服那些影响我们学习的大牛、小牛，抵制各种诱惑，集中精力，专心学习。
4、要有信心。英语不过是表达思想的一种工具、一种说话习惯而已。我们要坚信，只要有投入，有付出，就会有收获。绝不会“付出的爱收不回。”
5、要有实际行动。一个真正的马拉松运动员绝不会空等奥林匹克金牌从天下掉下来，现在就行动起来。
6、要有连续性、持续性。学英语是一个漫长的过程，走走停停便难有成就。比如烧开水，在烧到80度时停下来，等水冷了又烧，没烧开又停，如此周而复始，又费精力又费电，很难喝到水。学英语要一鼓作气。天天坚持，在完全忘记之前及时复习、加深印象，如此反复，直至形成永久性记忆。如果等到忘记了再来复习，就象又学新知识一样，那么，我们就永远是初学者，虽然在辛辛苦苦地烧开水，却难品味到其甘润。
2005年8月5日
Reading(7):Second Part-Semantic Interpretation
This part had so much information I had not known. I'd like to read it in detail.
---------------------------------------------------------------------------------
Pages: 179~188 of Natural Language Understanding, second edition, by James F. Allen, 1995
In the introduction, there was a useful sentence which indicated the basic idea of this part. That was there were two main steps for judging the meaning of a sentence. Firstly, context-free form, namely logical form should be calculated. Then, final semantic form generated by interpretation logic form in context. The research on context-free meaning was named as semantics. At same time, context-sensitive language research was named as pragmatics.
In this forthcoming content of this book there were two terms. Meaning meant context-free. Usage was related to context-sensitive.
Without question, ambiguity was the most serious problem of semantic interpretation. If a word could represented more than two meanings, we called it had semantically ambiguous.
Phases referring objects were context-sensitive. But some sentence structure would produce some referring bind.
For example, the object was different obviously in "Jack saw him in the mirror" and "Jack saw himself in the mirror." The most important task of Semantic Interpretation was reducing candidate senses of each word by bindings.
When objects described in context, we could use some discourse variables. When there was a new discourse variable occurred in context, it was named as a unique name. In common instance, the posterior sentences would point to it.
---------------------------------------------------------------------------------
---------------------------------------------------------------------------------
Pages: 179~188 of Natural Language Understanding, second edition, by James F. Allen, 1995
In the introduction, there was a useful sentence which indicated the basic idea of this part. That was there were two main steps for judging the meaning of a sentence. Firstly, context-free form, namely logical form should be calculated. Then, final semantic form generated by interpretation logic form in context. The research on context-free meaning was named as semantics. At same time, context-sensitive language research was named as pragmatics.
In this forthcoming content of this book there were two terms. Meaning meant context-free. Usage was related to context-sensitive.
Without question, ambiguity was the most serious problem of semantic interpretation. If a word could represented more than two meanings, we called it had semantically ambiguous.
Phases referring objects were context-sensitive. But some sentence structure would produce some referring bind.
For example, the object was different obviously in "Jack saw him in the mirror" and "Jack saw himself in the mirror." The most important task of Semantic Interpretation was reducing candidate senses of each word by bindings.
When objects described in context, we could use some discourse variables. When there was a new discourse variable occurred in context, it was named as a unique name. In common instance, the posterior sentences would point to it.
---------------------------------------------------------------------------------
2005年8月4日
Reading(6):Rule vs. Stat, Evaluation, Baseline
This morning, I wanted to write a program for the distribution of the existed knowledge base. Because I had not mastered C# for such task. I used C++ instead. I overloaded the operator "<" and "==" for sort and unique algorithms, respectively. Yes. C++ was effective for my task.
---------------------------------------------------------------------------------
Pages: 152~157 of Natural Language Understanding, second edition, by James F. Allen, 1995
I'd like to pick the useful information about this book. As the beginning chapters were about syntax parser, I changed my reading strategy. I reviewed the book and picked some useful segments. There were some useful skills for my NLP research. Just sharing them with you.
Evaluation:
To the most research topic in Machine learning and Natural Language processing, when we had the estimating probabilities set and the related algorithms, we would like to know the comparison between your method with other classical ones. The usual solution was dividing the corpus into training set and testing set. The classical share of testing data was 10% to 20% of total. Another refined testing method was cross validation. It used the different segments of all corpus for testing. Each time, different training set was used and new testing data was tested. Then average result was the final result. This method ensured the most likely testing result. I had seen lots of machine learning packages used this method. But in my research, I had not used any. I would try it in the forthcoming NLP experiments.
The importance of baseline:
How to measure the performance of an experiment? I believed that we must consider the difficulty of the problem. There was a concept named as Basline. It meant the performance run by the most simple method. Just like to part-of-speech tagging, if you chose the mostly result in the training corpus, you would achieve about 90% accuracy. It was amazing. The reason was that there were more than half the words of the corpus had single pos. Therefore, we could use this method as the baseline for evaluation complicated algorithms. Unless your method achieved far great than 90%, its effect was not good. To baseline, there was another concept I wanted to share with you. That was upper bound. It was the best result achieved by human craft. The closer your method to upper bound, the best was it.
---------------------------------------------------------------------------------
---------------------------------------------------------------------------------
Pages: 152~157 of Natural Language Understanding, second edition, by James F. Allen, 1995
I'd like to pick the useful information about this book. As the beginning chapters were about syntax parser, I changed my reading strategy. I reviewed the book and picked some useful segments. There were some useful skills for my NLP research. Just sharing them with you.
Evaluation:
To the most research topic in Machine learning and Natural Language processing, when we had the estimating probabilities set and the related algorithms, we would like to know the comparison between your method with other classical ones. The usual solution was dividing the corpus into training set and testing set. The classical share of testing data was 10% to 20% of total. Another refined testing method was cross validation. It used the different segments of all corpus for testing. Each time, different training set was used and new testing data was tested. Then average result was the final result. This method ensured the most likely testing result. I had seen lots of machine learning packages used this method. But in my research, I had not used any. I would try it in the forthcoming NLP experiments.
The importance of baseline:
How to measure the performance of an experiment? I believed that we must consider the difficulty of the problem. There was a concept named as Basline. It meant the performance run by the most simple method. Just like to part-of-speech tagging, if you chose the mostly result in the training corpus, you would achieve about 90% accuracy. It was amazing. The reason was that there were more than half the words of the corpus had single pos. Therefore, we could use this method as the baseline for evaluation complicated algorithms. Unless your method achieved far great than 90%, its effect was not good. To baseline, there was another concept I wanted to share with you. That was upper bound. It was the best result achieved by human craft. The closer your method to upper bound, the best was it.
---------------------------------------------------------------------------------
2005年8月3日
Reading(5): Syntax and its Analysis
Now I was doing some research on dialogue modeling and management. The more I learned more, the more important I felt about Natural Language Understanding. This evening, we would have the weekly Ping Pong club activity in BUAA. So I read the book in the afternoon after our project discussion.
---------------------------------------------------------------------------------
Pages: 31~40 of Natural Language Understanding, second edition, by James F. Allen, 1995
How to calculate the syntax of a sentence? In order to solve this problem, there were two aspects should be considered: Grammar of language and syntax parser technology. To a new language grammar, we cared about its universality, selectivity , and comprehensibility.
How to confirm whether some words could construct some special grammar component? There were two ways. One was constructing a new sentence. In this sentence, some congeneric component used as an paratactic. This was a very good method. As mostly, only same congeneric grammar component could be used as coordinative. The other way was inserting the component into other sentences and checking whether it could be as same grammar component.
There were two kinds of grammar parsers: Top-down and bottom-up. They were same as the process of program compilers. So I introduced it little there.
When researching grammar, you would find that each grammar component had many kinds of usages. Therefore you should try more times in order to check whether it was true of grammar. Meanwhile, you must modify the grammar for the new forms. Under the limited knowledge background, such backdating was necessary. However there was a very key point. That was you must review carefully the new rule and its relation between existed others in detail. I believed it was same as our rule-based system. Sometimes you add a new rule for some special situation now, and there were some many contrary instances to it. So, you must do it very carefully. I believed our language, such as English and Chinese, had not grammar. And many linguists added some rules for them based on some observation. This process was great exploits to humans.
---------------------------------------------------------------------------------
Pages: 31~40 of Natural Language Understanding, second edition, by James F. Allen, 1995
How to calculate the syntax of a sentence? In order to solve this problem, there were two aspects should be considered: Grammar of language and syntax parser technology. To a new language grammar, we cared about its universality, selectivity , and comprehensibility.
How to confirm whether some words could construct some special grammar component? There were two ways. One was constructing a new sentence. In this sentence, some congeneric component used as an paratactic. This was a very good method. As mostly, only same congeneric grammar component could be used as coordinative. The other way was inserting the component into other sentences and checking whether it could be as same grammar component.
There were two kinds of grammar parsers: Top-down and bottom-up. They were same as the process of program compilers. So I introduced it little there.
When researching grammar, you would find that each grammar component had many kinds of usages. Therefore you should try more times in order to check whether it was true of grammar. Meanwhile, you must modify the grammar for the new forms. Under the limited knowledge background, such backdating was necessary. However there was a very key point. That was you must review carefully the new rule and its relation between existed others in detail. I believed it was same as our rule-based system. Sometimes you add a new rule for some special situation now, and there were some many contrary instances to it. So, you must do it very carefully. I believed our language, such as English and Chinese, had not grammar. And many linguists added some rules for them based on some observation. This process was great exploits to humans.
2005年8月2日
Reading(4):Linguistic background knowledge of English syntax outline
To my experience on reading book these days, I found the time span was fixed. If I worked in the morning and afternoon, then I would spend evening time for reading. And then if I spent morning time, I could work in evening time. As the working principle, I chose to finish the reading task firstly.
---------------------------------------------------------------------------------
Pages: 21~30 of Natural Language Understanding, second edition, by James F. Allen, 1995
The ten pages was the main of chapter 2 'Linguistic background knowledge of English syntax outline.' In this chapter English phase structure was mainly introduced. There were materials about noun phrase, sentence, preposition phrase, adjective phrase, and adverb phrase. They all were about English syntax. So I felt about reviewing English knowledge that was learned in high school and freshman grade of undergraduate. There was some new cognition about English noun phrase. As the experience of ACE EDR evaluation, the most difficult task was noun phrase identification. There were so many kinds of conditions. In chapter 2.4 there was some deep introduction about noun phrase. I believed it was the same problem in ACE evaluation. I should pay more attention to it.
There was some related reading material about English syntax. Baker 1989 had give an perfect summarize. The most roundly materials were the books which tried to describe all the English structure, such as Huddleston(1988), Quick(1972), Leech and Svartvik(1975).
Reference:
Baker, C.L. 1989. English Syntax. Cambrige, MA: MIT Press
Huddleston, R. 1988. English Grammar: An Outline. New York: Cambridge U.Press.
Quick, R., S. Greenbaum, G.Leech, and J. Svartik. 1972. A Grammar of Contemporary English. New Your: Seminar Press.
Leech, G., and J. Svartvik. 1975. A communicative Grammar of English. Singapore: Longman Singapore Publishs Ltd.
---------------------------------------------------------------------------------
Tomorrow, I would start reading chapter 3 Syntax and its Analysis
---------------------------------------------------------------------------------
Pages: 21~30 of Natural Language Understanding, second edition, by James F. Allen, 1995
The ten pages was the main of chapter 2 'Linguistic background knowledge of English syntax outline.' In this chapter English phase structure was mainly introduced. There were materials about noun phrase, sentence, preposition phrase, adjective phrase, and adverb phrase. They all were about English syntax. So I felt about reviewing English knowledge that was learned in high school and freshman grade of undergraduate. There was some new cognition about English noun phrase. As the experience of ACE EDR evaluation, the most difficult task was noun phrase identification. There were so many kinds of conditions. In chapter 2.4 there was some deep introduction about noun phrase. I believed it was the same problem in ACE evaluation. I should pay more attention to it.
There was some related reading material about English syntax. Baker 1989 had give an perfect summarize. The most roundly materials were the books which tried to describe all the English structure, such as Huddleston(1988), Quick(1972), Leech and Svartvik(1975).
Reference:
Baker, C.L. 1989. English Syntax. Cambrige, MA: MIT Press
Huddleston, R. 1988. English Grammar: An Outline. New York: Cambridge U.Press.
Quick, R., S. Greenbaum, G.Leech, and J. Svartik. 1972. A Grammar of Contemporary English. New Your: Seminar Press.
Leech, G., and J. Svartvik. 1975. A communicative Grammar of English. Singapore: Longman Singapore Publishs Ltd.
---------------------------------------------------------------------------------
Tomorrow, I would start reading chapter 3 Syntax and its Analysis
2005年8月1日
Reading(3):Architecture, Word, and Noun Phrase
This afternoon, we four VSs had the group discussion with Prof. Zhou. We finished our discussion at 18:30. It was late for super. We went to Luck of Four Seasons restaurant of B1 in Sigma Building. We four were so hungry to have supper quickly and full all. After a tiring day, we all wanted to return to BUAA for rest. But to my reading habit, I stayed here and read the third times of Natural Language Understanding.
---------------------------------------------------------------------------------
Pages: 11~20 of Natural Language Understanding, second edition, by James F. Allen, 1995
NLU System Architecture:
The basic organization of this book was on three layers: syntax structure, logic form, and final expression of meaning. To each sentence, the intention relied much on its context. The context-free sense form of a sentence was its logic form. Logic form encoded possible word senses and expressed the relations between words and phrases. The final expression of meaning was the universal knowledge representation. Mostly, we used first-order predicate calculus ( FOPC ) as our expression language. Because it was fine-defined and well-known, the process of converting syntax structure and logic expression to final expression of meaning was named as context process. It included coreference and anaphora resolution, analysis the tense of sentence new information, confirming speaker's intention, and reasoning process of interpretation this sentence.
To chapter 2, English syntax outline
Word and noun phrase:
There were so many factors of word, such as tense, derivative, number, and gender. Noun phrase used for describing things, for instance, objects, place, concept, event, and quality. The most basic noun phrase included unitary pronouns, including ‘he’, ‘she’, ‘they’, ‘you’, ‘me’, ‘it’, and ‘I’. The other form was proper noun, such as "John" and "Rochester". The boundary of noun phrase was very complicated. For the ACE evaluation 2004, we had tried our best but achieved lower performance. There were so many situation of it that the best way was based on statistical analysis. Noun phrase might include specifiers and qualifiers. Specifiers could be categorized as article, demonstrative, possessive, wh-determiner, and quantifying determiner. Qualifiers included adjective, noun qualifiers. There were two kinds of noun: singular and plural.
---------------------------------------------------------------------------------
When I was in the working days of a week, I only had the evening every day for keeping reading habit. I could not do some practice every day. So I might change my life habit. Maybe doing morning exercise was the better way for it. I could try the morning practice habit for my reading habit. Just another habit. Why not try again following the rules of how to keep a habit in my blog.^_^
---------------------------------------------------------------------------------
Pages: 11~20 of Natural Language Understanding, second edition, by James F. Allen, 1995
NLU System Architecture:
The basic organization of this book was on three layers: syntax structure, logic form, and final expression of meaning. To each sentence, the intention relied much on its context. The context-free sense form of a sentence was its logic form. Logic form encoded possible word senses and expressed the relations between words and phrases. The final expression of meaning was the universal knowledge representation. Mostly, we used first-order predicate calculus ( FOPC ) as our expression language. Because it was fine-defined and well-known, the process of converting syntax structure and logic expression to final expression of meaning was named as context process. It included coreference and anaphora resolution, analysis the tense of sentence new information, confirming speaker's intention, and reasoning process of interpretation this sentence.
To chapter 2, English syntax outline
Word and noun phrase:
There were so many factors of word, such as tense, derivative, number, and gender. Noun phrase used for describing things, for instance, objects, place, concept, event, and quality. The most basic noun phrase included unitary pronouns, including ‘he’, ‘she’, ‘they’, ‘you’, ‘me’, ‘it’, and ‘I’. The other form was proper noun, such as "John" and "Rochester". The boundary of noun phrase was very complicated. For the ACE evaluation 2004, we had tried our best but achieved lower performance. There were so many situation of it that the best way was based on statistical analysis. Noun phrase might include specifiers and qualifiers. Specifiers could be categorized as article, demonstrative, possessive, wh-determiner, and quantifying determiner. Qualifiers included adjective, noun qualifiers. There were two kinds of noun: singular and plural.
---------------------------------------------------------------------------------
When I was in the working days of a week, I only had the evening every day for keeping reading habit. I could not do some practice every day. So I might change my life habit. Maybe doing morning exercise was the better way for it. I could try the morning practice habit for my reading habit. Just another habit. Why not try again following the rules of how to keep a habit in my blog.^_^
订阅：
博文 (Atom)