The Graduation Thesis phrase has been over. And tomorrow I will go to another phrase. Just now I have finished my brief summary of last month. And I have made a short plan for next month.
There are five main tasks for me: learning machine learning, work for ACE, evaluation for summarization, more detailed survey of coreference resolution, dll modules for Yuhaibin.
They are important for our lab and for me. I could try my best to finish them. They would give me a rich and happy summer vacation.
2004年6月29日
Thesis oral defends
This morning I improved my ppt for thesis oral defends. And at about three o'clock this afternoon, it was my turn to give the thesis oral denfends.
First, I gave a short introduction of my ppt. And then I talked about the research background, relating research survey home and abord, my research strategy. Finally I offered the conclusion of my research. Mr.Chen was interested in my research and asked me some questions.
The defense was short. It meant that my undergraduating graduation thesis had been finished.
Tomorrow I could do want I want and need to! :)
First, I gave a short introduction of my ppt. And then I talked about the research background, relating research survey home and abord, my research strategy. Finally I offered the conclusion of my research. Mr.Chen was interested in my research and asked me some questions.
The defense was short. It meant that my undergraduating graduation thesis had been finished.
Tomorrow I could do want I want and need to! :)
2004年6月28日
Print Our Graduation Thesis
Tomorrow we would give our thesis oral defends. So today was the deadline for printing our graduation thesis.
This afternoon, Zsq, Wlj, Lxt and me came to print our papers. When we were printing, there were all kinds errors to us. My word file has some problems with the formwork. And after about three hours our graduation thesis had been printed out. We were exciting.
Now, we had to prepare the ppt for tomorrow's oral defense.
This afternoon, Zsq, Wlj, Lxt and me came to print our papers. When we were printing, there were all kinds errors to us. My word file has some problems with the formwork. And after about three hours our graduation thesis had been printed out. We were exciting.
Now, we had to prepare the ppt for tomorrow's oral defense.
2004年6月27日
BBS party
This afternoon, we,some BBS net friends of HIT relating to Matlab, Mathematicals, and Office-Tools, got together in L002.
The main points of this party was academic exchange of research tools. The promoters were Administrators of Matlab, Mathematical, and Office-tools. When I came to L001 on time, there were some problems with the projector. And I met the administer of Matlab Zjliu who was a legend person of BBS. He was vexedly testing his notebook computer.
At 2:00pm, the party began formally. Firstly, the Office-tools administrator gave us a introduction about how to use word. There were some new method about field. Secondly, the matlab administrator introduced some programs of matlab. The GUI programming of matlab was very powerful. Later, I gave some ppt pages about Decision trees algorithms and C5.0 Decision trees Demonstrate Software. The later other net friends talked about how to use the edit software LaTex.
This form of BBS party was wonderful. I thought so. I wish there were more parties like that. Thanks to the three administrators!
The main points of this party was academic exchange of research tools. The promoters were Administrators of Matlab, Mathematical, and Office-tools. When I came to L001 on time, there were some problems with the projector. And I met the administer of Matlab Zjliu who was a legend person of BBS. He was vexedly testing his notebook computer.
At 2:00pm, the party began formally. Firstly, the Office-tools administrator gave us a introduction about how to use word. There were some new method about field. Secondly, the matlab administrator introduced some programs of matlab. The GUI programming of matlab was very powerful. Later, I gave some ppt pages about Decision trees algorithms and C5.0 Decision trees Demonstrate Software. The later other net friends talked about how to use the edit software LaTex.
This form of BBS party was wonderful. I thought so. I wish there were more parties like that. Thanks to the three administrators!
2004年6月26日
One old classmate
I got a short message from one of my old middle school classmates. She was exciting to say that she had graduated.
Reminding our original dreams in a class metting, she hoped to be a best Chinese teacher. At that moment, I thought she was happy and exciting. And at this moment she was happy and exciting, too. Great! She was the first classmate of our middle school class who had carry out his dream.
And after some days she would be sent to a middle or high school to be a Chinese teacher. I hope she will do herself good job!
Reminding our original dreams in a class metting, she hoped to be a best Chinese teacher. At that moment, I thought she was happy and exciting. And at this moment she was happy and exciting, too. Great! She was the first classmate of our middle school class who had carry out his dream.
And after some days she would be sent to a middle or high school to be a Chinese teacher. I hope she will do herself good job!
2004年6月25日
Review my blog
These days my task is writing my graduating design log. And my plan was to copy some of my blog to the log notebook.
As I have written about half of the log notebook. I only choose some blog diaries to copy. I choose some diaries from October last year.
I have not read any of my blog specially. But when I read some diaries and the comments I fell I could bethink that scene and idea. Some diaries reminded me lots of things.
As I have written about half of the log notebook. I only choose some blog diaries to copy. I choose some diaries from October last year.
I have not read any of my blog specially. But when I read some diaries and the comments I fell I could bethink that scene and idea. Some diaries reminded me lots of things.
2004年6月24日
Zjliu
This evening, I was lucky to see Zjliu who was the Editor of Matlab and Math of HIT Lilac. He was a legend people.
Firstly, he was sitting directly before my chair. And after the teacher's name checking, he spoke his name. At that moment I, with my partner, was exciting. When I observed him carefully, he was the studious type. I thought so.
Good luck! And after the recent emails and some short talk, I thought I had been little familiar with him.
Firstly, he was sitting directly before my chair. And after the teacher's name checking, he spoke his name. At that moment I, with my partner, was exciting. When I observed him carefully, he was the studious type. I thought so.
Good luck! And after the recent emails and some short talk, I thought I had been little familiar with him.
2004年6月23日
Translating the paper
There was one sub-task of our graduating design. That was translating a directly related English paper into Chinese. From last morning I began to translate Corpus-Based Learning for Noun Phrase Coreference Resolution that was written by Soon.
When I had translated the paper, I found I understood it more clearly. Yeah. This a good way for understanding some classical paper.
There was a workshop of ACL to coreference resolution. The related papers was published on the Computational Linguistic. I could use this way for understanging them!
When I had translated the paper, I found I understood it more clearly. Yeah. This a good way for understanding some classical paper.
There was a workshop of ACL to coreference resolution. The related papers was published on the Computational Linguistic. I could use this way for understanging them!
2004年6月22日
用Word编辑论文的几个建议
看到小百合上12ee 的blog里面一篇关于word排版的文章，摘来保存，留待学习和与大家共享：
用Word编辑论文的几个建议(zz)
Thu Jun 3 10:36:56 2004
原则: 内容与表现分离
====================
一篇论文应该包括两个层次的含义：内容与表现，前者是指文章作者用来表达自己思想的文字、图片、表格、公式及整个文章的章节段落结构等，而后者则是指论文页面大小、边距、各种字体、字号等。相同的内容可以有不同的表现，例如一篇文章在不同的出版社出版会有不同的表现；而不同的内容可以使用相同的表现，例如一个期刊上发表的所有文章的表现都是相同的。这两者的关系不言自明。在排版软件普及之前，作者只需关心文章的内容，文章表现则由出版社的排版工人完成，当然他们之间会有一定交互。Word 倡导一种所见即所得（WYSIWYG）的方式,将编辑和排版集成在一起，使得作者在处理内容的同时就可以设置并立即看到其表现。可惜的是很多作者滥用WYSIWYG，将内容与表现混杂在一起，花费了大量的时间在人工排版上，然而效率和效果都很差。本文所强调的“内容与表现分离”的原则就是说文章作者只要关心文章的内容，所有与内容无关的排版工作都交给 Word 去完成，作者只需将自己的排版意图以适当的方式告诉 Word。因为Word不仅仅是一个编辑器，还是一个排版软件，不要只拿它当记事本或写字板用。主要建议如下。
1. 一定要使用样式，除了Word原先所提供的标题、正文等样式外，还可以自定义样式。如果你发现自己是用选中文字然后用格式栏来设定格式的，一定要注意，想想其他地方是否需要相同的格式，如果是的话，最好就定义一个样式。对于相同排版表现的内容一定要坚持使用统一的样式。这样做能大大减少工作量和出错机会，如果要对排版格式（文档表现）做调整，只需一次性修改相关样式即可。使用样式的另一个好处是可以由Word 自动生成各种目录和索引。
2. 一定不要自己敲编号，一定要使用交叉引用。如果你发现自己打了编号，一定要小心，这极可能给你文章的修改带来无穷的后患。标题的编号可以通过设置标题样式来实现，表格和图形的编号通过设置题注的编号来完成。在写“参见第x章、如图x所示”等字样时，不要自己敲编号，应使用交叉引用。这样做以后，当插入或删除新的内容时，所有的编号和引用都将自动更新，无需人力维护。并且可以自动生成图、表目录。公式的编号虽然也可以通过题注来完成，但我另有建议，见5。
3. 一定不要自己敲空格来达到对齐的目的。只有英文单词间才会有空格，中文文档没有空格。所有的对齐都应该利用标尺、制表位、对齐方式和段落的缩进等来进行。如果发现自己打了空格，一定要谨慎，想想是否可以通过其他方法来避免。同理，一定不要敲回车来调整段落的间距。
4. 绘图。统计图建议使用Execel生成，框图和流程图建议使用Visio画。如果不能忍受Vi
sio对象复制到Word的速度，还可以试试SmardDraw，功能不比Visio弱，使用不比Visio难，速度却快多了。如果使用Word的绘图工具绘图，最好以插入Word图片的方式，并适当使用组合。
5. 编辑数学公式建议使用 MathType5.0，其实Word集成的公式编辑器是它的3.0版。安装MathType后，Word会增加一个菜单项，其功能一目了然。一定要使用 MathType 的自动编号和引用功能。这样首先可以有一个良好的对齐，还可以自动更新编号。Word 正文中插入公式的一个常见问题是把上下行距都撑大了，很不美观，这部分可以通过固定行距来修正。
6. 参考文献的编辑和管理。如果你在写论文时才想到要整理参考文献，已经太迟了，但总比论文写到参考文献那一页时才去整理要好。应该养成看文章的同时就整理参考文献的习惯。手工整理参考文献是很痛苦的，而且很容易出错。Word没有提供管理参考文献的功能，用插入尾注的方法也很不地道。我建议使用 Reference Manager，它与Word集成得非常好，提供即写即引用（Cite while you write，简称Cwyw）的功能。你所做的只是像填表格一样地输入相关信息，如篇名、作者、年份等在文章中需要引用文献的的方插入标记，它会为你生成非常美观和专业的参考文献列表，并且对参考文献的引用编号也是自动生成和更新的。这除了可以保持格式上的一致、规范，减少出错机会外，更可以避免正文中对参考文献的引用和参考文献列表之间的不匹配。并且从长远来说，本次输入的参考文献信息可以在今后重复利用，从而一劳永逸。类似软件还有Endnote和Biblioscape。Endnote优点在于可以将文献列表导出到BibTeX格式，但功能没有Reference Manager强大。可惜这两个软件都不支持中文，据说Biblioscape对中文支持的很好，我没有用过，就不加评论了。
7.使用节。如果希望在一片文档里得到不同的页眉、页脚、页码格式，可以插入分节符，并设置当前节的格式与上一节不同。
上述7点都是关于排版的建议，还是要强调一遍，作者关心的重点是文章的内容，文章的表现就交给Word去处理。如果你发现自己正在做与文章内容无关的繁琐的排版工作，一定要停下来学一下Word的帮助，因为Word 早已提供了足够强大的功能。
我不怀疑Word的功能，但不相信其可靠性和稳定性，经常遇到“所想非所见”、“所见非所得”的情况让人非常郁闷。如果养成良好的习惯，这些情况也可以尽量避免，即使遇上，也可以将损失降低到最低限度。建议如下：
8.使用子文档。学位论文至少要几十页，且包括大量的图片、公式、表格，比较庞大。如果所有的内容都保存在一个文件里，打开、保存、关闭都需要很长的时间，且不保险。建议论文的每一章保存到一个子文档，而在主控文档中设置样式。这样每个文件小了，编辑速度快，而且就算文档损坏，也只有一章的损失，不至于全军覆灭。建议先建主控文档，从主控文档中创建子文档，个人感觉比先写子文档再插入到主控文档要好。
9.及时保存，设置自动保存，还有一有空就ctrl+s。
10.多做备份，不但Word不可靠，windows也不可靠，每天的工作都要有备份才好。注意分清版本，不要搞混了。Word提供了版本管理的功能，将一个文档的各个版本保存到一个文件里，并提供比较合并等功能。不过保存几个版本后文件就大得不得了，而且一个文件损坏后所有的版本都没了，个人感觉不实用。还是多处备份吧
11.插入的图片、和公式最好单独保存到文件里另做备份。否则，哪天打文档时发现自己辛辛苦苦的编辑的图片和公式都变成了大红叉，哭都来不及了。
其他建议:
12. 使用大纲视图写文章的提纲，调整章节顺序比较方便
13. 使用文档结构图让你方便的定位章节
14. 使用文档保护，方便文章的审阅和修改
15. Word表格的排序、公式和转换的功能也是很值得学习的
用Word编辑论文的几个建议(zz)
Thu Jun 3 10:36:56 2004
原则: 内容与表现分离
====================
一篇论文应该包括两个层次的含义：内容与表现，前者是指文章作者用来表达自己思想的文字、图片、表格、公式及整个文章的章节段落结构等，而后者则是指论文页面大小、边距、各种字体、字号等。相同的内容可以有不同的表现，例如一篇文章在不同的出版社出版会有不同的表现；而不同的内容可以使用相同的表现，例如一个期刊上发表的所有文章的表现都是相同的。这两者的关系不言自明。在排版软件普及之前，作者只需关心文章的内容，文章表现则由出版社的排版工人完成，当然他们之间会有一定交互。Word 倡导一种所见即所得（WYSIWYG）的方式,将编辑和排版集成在一起，使得作者在处理内容的同时就可以设置并立即看到其表现。可惜的是很多作者滥用WYSIWYG，将内容与表现混杂在一起，花费了大量的时间在人工排版上，然而效率和效果都很差。本文所强调的“内容与表现分离”的原则就是说文章作者只要关心文章的内容，所有与内容无关的排版工作都交给 Word 去完成，作者只需将自己的排版意图以适当的方式告诉 Word。因为Word不仅仅是一个编辑器，还是一个排版软件，不要只拿它当记事本或写字板用。主要建议如下。
1. 一定要使用样式，除了Word原先所提供的标题、正文等样式外，还可以自定义样式。如果你发现自己是用选中文字然后用格式栏来设定格式的，一定要注意，想想其他地方是否需要相同的格式，如果是的话，最好就定义一个样式。对于相同排版表现的内容一定要坚持使用统一的样式。这样做能大大减少工作量和出错机会，如果要对排版格式（文档表现）做调整，只需一次性修改相关样式即可。使用样式的另一个好处是可以由Word 自动生成各种目录和索引。
2. 一定不要自己敲编号，一定要使用交叉引用。如果你发现自己打了编号，一定要小心，这极可能给你文章的修改带来无穷的后患。标题的编号可以通过设置标题样式来实现，表格和图形的编号通过设置题注的编号来完成。在写“参见第x章、如图x所示”等字样时，不要自己敲编号，应使用交叉引用。这样做以后，当插入或删除新的内容时，所有的编号和引用都将自动更新，无需人力维护。并且可以自动生成图、表目录。公式的编号虽然也可以通过题注来完成，但我另有建议，见5。
3. 一定不要自己敲空格来达到对齐的目的。只有英文单词间才会有空格，中文文档没有空格。所有的对齐都应该利用标尺、制表位、对齐方式和段落的缩进等来进行。如果发现自己打了空格，一定要谨慎，想想是否可以通过其他方法来避免。同理，一定不要敲回车来调整段落的间距。
4. 绘图。统计图建议使用Execel生成，框图和流程图建议使用Visio画。如果不能忍受Vi
sio对象复制到Word的速度，还可以试试SmardDraw，功能不比Visio弱，使用不比Visio难，速度却快多了。如果使用Word的绘图工具绘图，最好以插入Word图片的方式，并适当使用组合。
5. 编辑数学公式建议使用 MathType5.0，其实Word集成的公式编辑器是它的3.0版。安装MathType后，Word会增加一个菜单项，其功能一目了然。一定要使用 MathType 的自动编号和引用功能。这样首先可以有一个良好的对齐，还可以自动更新编号。Word 正文中插入公式的一个常见问题是把上下行距都撑大了，很不美观，这部分可以通过固定行距来修正。
6. 参考文献的编辑和管理。如果你在写论文时才想到要整理参考文献，已经太迟了，但总比论文写到参考文献那一页时才去整理要好。应该养成看文章的同时就整理参考文献的习惯。手工整理参考文献是很痛苦的，而且很容易出错。Word没有提供管理参考文献的功能，用插入尾注的方法也很不地道。我建议使用 Reference Manager，它与Word集成得非常好，提供即写即引用（Cite while you write，简称Cwyw）的功能。你所做的只是像填表格一样地输入相关信息，如篇名、作者、年份等在文章中需要引用文献的的方插入标记，它会为你生成非常美观和专业的参考文献列表，并且对参考文献的引用编号也是自动生成和更新的。这除了可以保持格式上的一致、规范，减少出错机会外，更可以避免正文中对参考文献的引用和参考文献列表之间的不匹配。并且从长远来说，本次输入的参考文献信息可以在今后重复利用，从而一劳永逸。类似软件还有Endnote和Biblioscape。Endnote优点在于可以将文献列表导出到BibTeX格式，但功能没有Reference Manager强大。可惜这两个软件都不支持中文，据说Biblioscape对中文支持的很好，我没有用过，就不加评论了。
7.使用节。如果希望在一片文档里得到不同的页眉、页脚、页码格式，可以插入分节符，并设置当前节的格式与上一节不同。
上述7点都是关于排版的建议，还是要强调一遍，作者关心的重点是文章的内容，文章的表现就交给Word去处理。如果你发现自己正在做与文章内容无关的繁琐的排版工作，一定要停下来学一下Word的帮助，因为Word 早已提供了足够强大的功能。
我不怀疑Word的功能，但不相信其可靠性和稳定性，经常遇到“所想非所见”、“所见非所得”的情况让人非常郁闷。如果养成良好的习惯，这些情况也可以尽量避免，即使遇上，也可以将损失降低到最低限度。建议如下：
8.使用子文档。学位论文至少要几十页，且包括大量的图片、公式、表格，比较庞大。如果所有的内容都保存在一个文件里，打开、保存、关闭都需要很长的时间，且不保险。建议论文的每一章保存到一个子文档，而在主控文档中设置样式。这样每个文件小了，编辑速度快，而且就算文档损坏，也只有一章的损失，不至于全军覆灭。建议先建主控文档，从主控文档中创建子文档，个人感觉比先写子文档再插入到主控文档要好。
9.及时保存，设置自动保存，还有一有空就ctrl+s。
10.多做备份，不但Word不可靠，windows也不可靠，每天的工作都要有备份才好。注意分清版本，不要搞混了。Word提供了版本管理的功能，将一个文档的各个版本保存到一个文件里，并提供比较合并等功能。不过保存几个版本后文件就大得不得了，而且一个文件损坏后所有的版本都没了，个人感觉不实用。还是多处备份吧
11.插入的图片、和公式最好单独保存到文件里另做备份。否则，哪天打文档时发现自己辛辛苦苦的编辑的图片和公式都变成了大红叉，哭都来不及了。
其他建议:
12. 使用大纲视图写文章的提纲，调整章节顺序比较方便
13. 使用文档结构图让你方便的定位章节
14. 使用文档保护，方便文章的审阅和修改
15. Word表格的排序、公式和转换的功能也是很值得学习的
2004年6月21日
Concentrated on writing graduating design paper
Concentrated on writing graduating design paper, this was my whole day's work.
And just now I have finished most of the paper. Tomorrow I could write some acknowledgement words and translate an English paper.
Ok. Keep on.
And just now I have finished most of the paper. Tomorrow I could write some acknowledgement words and translate an English paper.
Ok. Keep on.
2004年6月20日
Father's day
This is Father's day. Following my original habit, I phoned my father this evening. He was happy to hear my bless. And we talked much about the family life.
Yes. My father is great in my opinion. He is encouraging me to do better.
Thanks to my father!!
Yes. My father is great in my opinion. He is encouraging me to do better.
Thanks to my father!!
2004年6月19日
English Band Six Exam
This afternoon we had the English band six exam. There were some excited information I wanted to share with you!
There were 30 vocabulary subjects. And there was one subject's main idea as follows:
We know computer are used to store information and _____ information.
And "retrieve" was an optional choice.
At that time, I chose the "retrieve" without striking a blowing. I was excited. Because our lab was information retrieval lab. I thought I was lucky. Because if I was not in our lab, maybe I couldn't make the correct choice at that time.
So lucky, I think I could pass it this time ^_^
There were 30 vocabulary subjects. And there was one subject's main idea as follows:
We know computer are used to store information and _____ information.
And "retrieve" was an optional choice.
At that time, I chose the "retrieve" without striking a blowing. I was excited. Because our lab was information retrieval lab. I thought I was lucky. Because if I was not in our lab, maybe I couldn't make the correct choice at that time.
So lucky, I think I could pass it this time ^_^
2004年6月18日
Writing my graduating design paper.
There were only ten days left for me to write my graduating design paper. And last morning, Mrs.Qin had checked my program out. I began to write from yesterday.
And right now I have written two chapters. The left time was little. I would hold all my time for it!
This afternoon, I discussed some basic concepts with Mjs. And the concept of Chinese BaseNP confused me. Dr.Tliu gave us some suggestion that we should find out the fittest concept for our research.
And right now I have written two chapters. The left time was little. I would hold all my time for it!
This afternoon, I discussed some basic concepts with Mjs. And the concept of Chinese BaseNP confused me. Dr.Tliu gave us some suggestion that we should find out the fittest concept for our research.
2004年6月17日
Ardent discuss
Ardent discuss! Yeah, I think so.
This afternoon, we were discussing the paraphrase in our IR-BBS. And this evening we were discussing whether the coreference resolution should process BaseNP or MNP.
After the ardent discuss, I thought we were be more clearly to these basic concept. Good form.
This afternoon, we were discussing the paraphrase in our IR-BBS. And this evening we were discussing whether the coreference resolution should process BaseNP or MNP.
After the ardent discuss, I thought we were be more clearly to these basic concept. Good form.
2004年6月16日
Splendid moment
This afternoon, our grade had the total group photo and each class had their own group photo. I think the photoing time was the splendid moment.
Our class group photo was as follows:
Our class group photo was as follows:
2004年6月15日
指代消解系统的检查
上午IE小组开会讨论IE系统的构建和文摘的系统方案。会间提到了指代消解，我将做完做好的指代消解系统向大家展示了一下。
刘老师的意见是现在的系统中包含的全匹配的样例太多，而代词的指代消解的正确率还很低。这样将Coreference resolution和anaphora resolution 合并在一起进行指代消解的研究需要细化。下一步可以将指代消解的各种情况分门别类的进行研究。
仔细分析发现完成的IRCR系统的采用的上次完成的决策树进行消解时规则过于简单。对于现在完成的系统需要进行代词短语的指代消解的解决。目前想到的解决方案是在处理“他”“她”等问题时采用一个baseline技术，即查找最近邻的性、数一致的人名或代词来实现消解。这个问题下午必须解决。
刘老师的意见是现在的系统中包含的全匹配的样例太多，而代词的指代消解的正确率还很低。这样将Coreference resolution和anaphora resolution 合并在一起进行指代消解的研究需要细化。下一步可以将指代消解的各种情况分门别类的进行研究。
仔细分析发现完成的IRCR系统的采用的上次完成的决策树进行消解时规则过于简单。对于现在完成的系统需要进行代词短语的指代消解的解决。目前想到的解决方案是在处理“他”“她”等问题时采用一个baseline技术，即查找最近邻的性、数一致的人名或代词来实现消解。这个问题下午必须解决。
指代消解系统的完成
上午的检查中发现我的系统中对代词的指代消解基本都错了。下午在决策树的规则的前面我加入了大约七条规则来完成针对代词的指代消解，不断修正调试后感觉就目前的水平而言，基本完成了指代消解任务。下一步就是要开始从明天开始撰写毕业论文了。
这里给出完成的一篇指代消解的文章：
妈妈的[园子]1
我们的[房子]2前院，後院都是长满肯塔基蓝草的绿毯子，修剪得平平坦坦的。靠近[房子]2的地方有一小块可以种花的[园子]1。搬进这个家[时]3还是八月盛夏，忙乱中没留意。转眼初秋，和跑着跳着的儿子走进後院，才发现[叶子]4变成金黄和赭红的枫树底下，有这么一片小[天地]5，[自己]3的[天地]5。妻子轻声对[我]4说，妈妈在的话，一定会很喜欢这[园子]6。
在模糊的记忆中，[我们]4家曾拥有一块三角园子。[我]4从来没问过那片[园子]6[哪]7来，又到[哪]7去了。只依稀地记得那里长着叫不出名的果树，散发幽幽香气的[玉兰]8，和整整齐齐的菜畦。门上挂着把长满锈的大铁锁，门里安谧凉爽，和门外闹市竟成一种独特的反差。
[我]8猜[妈妈和土地]9结下的不解之缘多半和[那]10[园子]11有关，或许从爸爸妈妈二次世界大战时在大後方贵阳红十字会的小菜园开始。可是[我]8永远也不知道[她]9在[那]10[园子]11里的乐趣和苦恼。
没到[我]8真懂事，绿色便无偿地被灰色代替，变成[竹]12棚搭起来的工厂，後来又长出高楼，[园子]11离[我们]12越来越远，直至消失。[每]8走过[那]10片三角“飞地”，[我]8老爱想像[那]10再也不存在的树阴和泥香，抬着头看看那些果树是否还会钻出水泥地，穿过楼层，长到屋顶上。
[妈妈]13总有一片[园子]11。[我]8[刚]14开始懂事时，[妈妈]13的[园子]11里有最美妙的天地。[妈妈]13会讲[故事]15，[她]13给[她]13的学生讲，给[我]8的同学讲，讲动人的过去和神奇的未来，讲做好孩子的哲理，晚上[我]8听着[故事]15入睡。[妈妈]13会做衣服，在桌子上量呀剪呀，用家里[那]16老古董手摇缝纫机缝啊钉啊，把[我们]14兄弟姐妹五个打扮得整整齐齐。周末，节日，[妈妈]13会下厨房切呀炒啊，变戏法似地做出好吃的菜，看着[我们]14几个风卷残云。最吸引人的，是[妈妈]13任教的[那]16片[天地]17。[妈妈]13教的是生物，[她]13的[天地]17里有栩栩如生的模型，泡着药水的标本，还有一片实验园地。[每年]13不多的几次，[妈妈]13带[我]18去[那]16片在校园围墙边上的实验地。[我]18在一旁，听[她]13跟学生讲种子发芽、开花结果，好奇[地]17看着光合作用的挂图，带着恐惧寻找菜叶上胖胖的虫子。收获时节，西红柿鲜红，麦子金黄，[我]18则最爱在[地瓜]19陇中，花生地里翻，体验发现新大陆似的惊喜。[我]18有问不完的问题，[妈妈]20有用不尽的答案。有一天，[我]18似懂非懂[地]19告诉[妈妈]20，[我]18也知道“粒粒皆辛苦”了。
家里也是[妈妈]20的园子。长长的[阳台]21上摆[满]22了各种各样的植物，透过叶子可以看到远处的山。清早黄昏，[妈妈]20走出[阳台]21逐个照看，浇水施肥，[松]23土剪枝。风和日丽时，还会听到[她]22打几个响亮的喷嚏，到美国後才得知那或许也是花粉过敏。逢年过节，[我们]23家客厅总有盛开的盆花点缀，兰花，菊花，芍药，海棠。妈妈种了好些[昙花]24。每当好几朵[昙花]24将一起开的时候，[我们]23家会热闹起来。在那些仲夏的夜晚，[邻居朋友们]25都来观赏这别称“月下待[友]25”的[昙花]24，亲眼见见昙花一现。围着嫩红的花蕾，看[它们]24慢慢地[张]26开口，露出洁白的花瓣和长长的花芯，连最没耐心的[我]26也被[它]24的清丽吸引住了。但是[我]26总没能熬到下半夜以一睹[昙花]24昂首开放的雄姿，一觉醒来睡眼惺忪只看到低垂的花朵。[我]26问[妈妈]27能不能让[昙花]24在白天开花。[妈妈]27找来仙人掌作砧木，用刀片切开小口，仔细地把削好的昙花枝条楔进去，滴上蜡封住。嫁接的[昙花]24活了，长出小小的花芽，又慢慢长成弯弯翘起的[昙花]24。我期待奇迹出现。[妈妈]28说，第一次嫁接的[昙花]24可能还是晚上开的。要经过多次嫁接改良，慢慢拨动[昙花]24的生物钟，才可能看到白天的[昙花]24。象打开通向奇妙宫殿的大门，我迷上《十万个[为什么]28》，曾经把挂钟拆成碎片的一双手有了用场。[妈妈]29教[我们]30浸泡[西红柿种子]31，发芽了以後移植到花盆里。哥哥种的[西红柿]31长得好，[妈妈]29拿药水滴在[西红柿]31的花上，结果长出又大又甜的无籽番茄，还引来後来没有好下场的两只大老鼠。
十年前[我]32飘洋过海，留下临分娩的[妻子]33，那时[我们]30的小家庭刚刚搬进[梅花村]34。[妈妈]29退了休，从老家到[梅花村]34来照顾[妻子]33。儿子降生後的繁忙中，[妈妈]29忘不了、离不开[她]29的[园子]35，和[妻子]33一起把原来堆满废土的小院子换上生机嫣然的绿色，告诉[我]32这样才和[梅花村]34幽雅的环境相配。[我]32只能凭信和照片编织[妈妈]29沿着围墙洒下的玫瑰花，海棠花，还有嫁接在仙人掌上的蟹兰。[我]32给[妈妈]29捎去这里随处可见的花园和绿草，[妈妈]29给[我]32描绘[她]29的[园子]35里天天长大的小调皮鬼，和[她]29最得意的珠顶兰花。[我]32时时想念老家阳台上的花草，惦记着梅花村那个小院子。
[妈妈]29的[园子]35里永远丰硕。好些年後，长成了大男孩的儿子和我们在北美团聚，[我]32开始在大学任教。当[那]36用难以辨认的字体印的博士学位证书寄到[妈妈]29手里，[我]32知道[妈妈]29和[我]32一样高兴。揣着[我]32[那]36封不知看过[多少]32遍的信，[我]32相信[妈妈]29还在等[我]32带郁金香的种子回去。[多少]29个白天黑夜，听着[妈妈导演]37的录音带里儿子小时候奶声奶气的歌谣，[我]32等待着[妈妈]29到美国来，欣赏这里精心雕琢的花园，崇尚自然的公园。没想到这却成了永远的梦。妈妈一生辛劳，没有太多的言语，[她]37用一颗爱心，潜移默化地养育了两代人。十年後的夏天，我们回到我度过童年的老家。[阳台]38上的园子依然花草[茂盛]39，远处的山影被近处的楼房代替了。入夜，银色的月光穿过枝叶洒向地上，星星点点，在[微微]40的海风中闪闪烁烁地动着。傍着[阳台]38的栏杆，[我]39始终觉得[妈妈]41随时会从[楼梯]42走上来，拎着[她]39上班的小黑包，一样的笑容，一样的活力。于是，[我]40竖起耳朵听着[楼梯]42的脚步声。于是，就有了把[这]43十年的苦[乐]44，十年的情怀告诉[妈妈]41的冲动。于是，就有了这个梦。[每]44到春天，[我们]44的[这]43片小天地上，[迎春]45花唤醒万物，先是兰花和郁金香破土而出，继而杜鹃花含苞怒放，与满树的山茱萸花相映，深红的，淡紫的，鹅黄的，雪白的。就是那一天，[我]45梦见了，梦见了妈妈就在[这]43花丛中。
感觉结果还可以。明天开始写论文了 ^_^
这里给出完成的一篇指代消解的文章：
妈妈的[园子]1
我们的[房子]2前院，後院都是长满肯塔基蓝草的绿毯子，修剪得平平坦坦的。靠近[房子]2的地方有一小块可以种花的[园子]1。搬进这个家[时]3还是八月盛夏，忙乱中没留意。转眼初秋，和跑着跳着的儿子走进後院，才发现[叶子]4变成金黄和赭红的枫树底下，有这么一片小[天地]5，[自己]3的[天地]5。妻子轻声对[我]4说，妈妈在的话，一定会很喜欢这[园子]6。
在模糊的记忆中，[我们]4家曾拥有一块三角园子。[我]4从来没问过那片[园子]6[哪]7来，又到[哪]7去了。只依稀地记得那里长着叫不出名的果树，散发幽幽香气的[玉兰]8，和整整齐齐的菜畦。门上挂着把长满锈的大铁锁，门里安谧凉爽，和门外闹市竟成一种独特的反差。
[我]8猜[妈妈和土地]9结下的不解之缘多半和[那]10[园子]11有关，或许从爸爸妈妈二次世界大战时在大後方贵阳红十字会的小菜园开始。可是[我]8永远也不知道[她]9在[那]10[园子]11里的乐趣和苦恼。
没到[我]8真懂事，绿色便无偿地被灰色代替，变成[竹]12棚搭起来的工厂，後来又长出高楼，[园子]11离[我们]12越来越远，直至消失。[每]8走过[那]10片三角“飞地”，[我]8老爱想像[那]10再也不存在的树阴和泥香，抬着头看看那些果树是否还会钻出水泥地，穿过楼层，长到屋顶上。
[妈妈]13总有一片[园子]11。[我]8[刚]14开始懂事时，[妈妈]13的[园子]11里有最美妙的天地。[妈妈]13会讲[故事]15，[她]13给[她]13的学生讲，给[我]8的同学讲，讲动人的过去和神奇的未来，讲做好孩子的哲理，晚上[我]8听着[故事]15入睡。[妈妈]13会做衣服，在桌子上量呀剪呀，用家里[那]16老古董手摇缝纫机缝啊钉啊，把[我们]14兄弟姐妹五个打扮得整整齐齐。周末，节日，[妈妈]13会下厨房切呀炒啊，变戏法似地做出好吃的菜，看着[我们]14几个风卷残云。最吸引人的，是[妈妈]13任教的[那]16片[天地]17。[妈妈]13教的是生物，[她]13的[天地]17里有栩栩如生的模型，泡着药水的标本，还有一片实验园地。[每年]13不多的几次，[妈妈]13带[我]18去[那]16片在校园围墙边上的实验地。[我]18在一旁，听[她]13跟学生讲种子发芽、开花结果，好奇[地]17看着光合作用的挂图，带着恐惧寻找菜叶上胖胖的虫子。收获时节，西红柿鲜红，麦子金黄，[我]18则最爱在[地瓜]19陇中，花生地里翻，体验发现新大陆似的惊喜。[我]18有问不完的问题，[妈妈]20有用不尽的答案。有一天，[我]18似懂非懂[地]19告诉[妈妈]20，[我]18也知道“粒粒皆辛苦”了。
家里也是[妈妈]20的园子。长长的[阳台]21上摆[满]22了各种各样的植物，透过叶子可以看到远处的山。清早黄昏，[妈妈]20走出[阳台]21逐个照看，浇水施肥，[松]23土剪枝。风和日丽时，还会听到[她]22打几个响亮的喷嚏，到美国後才得知那或许也是花粉过敏。逢年过节，[我们]23家客厅总有盛开的盆花点缀，兰花，菊花，芍药，海棠。妈妈种了好些[昙花]24。每当好几朵[昙花]24将一起开的时候，[我们]23家会热闹起来。在那些仲夏的夜晚，[邻居朋友们]25都来观赏这别称“月下待[友]25”的[昙花]24，亲眼见见昙花一现。围着嫩红的花蕾，看[它们]24慢慢地[张]26开口，露出洁白的花瓣和长长的花芯，连最没耐心的[我]26也被[它]24的清丽吸引住了。但是[我]26总没能熬到下半夜以一睹[昙花]24昂首开放的雄姿，一觉醒来睡眼惺忪只看到低垂的花朵。[我]26问[妈妈]27能不能让[昙花]24在白天开花。[妈妈]27找来仙人掌作砧木，用刀片切开小口，仔细地把削好的昙花枝条楔进去，滴上蜡封住。嫁接的[昙花]24活了，长出小小的花芽，又慢慢长成弯弯翘起的[昙花]24。我期待奇迹出现。[妈妈]28说，第一次嫁接的[昙花]24可能还是晚上开的。要经过多次嫁接改良，慢慢拨动[昙花]24的生物钟，才可能看到白天的[昙花]24。象打开通向奇妙宫殿的大门，我迷上《十万个[为什么]28》，曾经把挂钟拆成碎片的一双手有了用场。[妈妈]29教[我们]30浸泡[西红柿种子]31，发芽了以後移植到花盆里。哥哥种的[西红柿]31长得好，[妈妈]29拿药水滴在[西红柿]31的花上，结果长出又大又甜的无籽番茄，还引来後来没有好下场的两只大老鼠。
十年前[我]32飘洋过海，留下临分娩的[妻子]33，那时[我们]30的小家庭刚刚搬进[梅花村]34。[妈妈]29退了休，从老家到[梅花村]34来照顾[妻子]33。儿子降生後的繁忙中，[妈妈]29忘不了、离不开[她]29的[园子]35，和[妻子]33一起把原来堆满废土的小院子换上生机嫣然的绿色，告诉[我]32这样才和[梅花村]34幽雅的环境相配。[我]32只能凭信和照片编织[妈妈]29沿着围墙洒下的玫瑰花，海棠花，还有嫁接在仙人掌上的蟹兰。[我]32给[妈妈]29捎去这里随处可见的花园和绿草，[妈妈]29给[我]32描绘[她]29的[园子]35里天天长大的小调皮鬼，和[她]29最得意的珠顶兰花。[我]32时时想念老家阳台上的花草，惦记着梅花村那个小院子。
[妈妈]29的[园子]35里永远丰硕。好些年後，长成了大男孩的儿子和我们在北美团聚，[我]32开始在大学任教。当[那]36用难以辨认的字体印的博士学位证书寄到[妈妈]29手里，[我]32知道[妈妈]29和[我]32一样高兴。揣着[我]32[那]36封不知看过[多少]32遍的信，[我]32相信[妈妈]29还在等[我]32带郁金香的种子回去。[多少]29个白天黑夜，听着[妈妈导演]37的录音带里儿子小时候奶声奶气的歌谣，[我]32等待着[妈妈]29到美国来，欣赏这里精心雕琢的花园，崇尚自然的公园。没想到这却成了永远的梦。妈妈一生辛劳，没有太多的言语，[她]37用一颗爱心，潜移默化地养育了两代人。十年後的夏天，我们回到我度过童年的老家。[阳台]38上的园子依然花草[茂盛]39，远处的山影被近处的楼房代替了。入夜，银色的月光穿过枝叶洒向地上，星星点点，在[微微]40的海风中闪闪烁烁地动着。傍着[阳台]38的栏杆，[我]39始终觉得[妈妈]41随时会从[楼梯]42走上来，拎着[她]39上班的小黑包，一样的笑容，一样的活力。于是，[我]40竖起耳朵听着[楼梯]42的脚步声。于是，就有了把[这]43十年的苦[乐]44，十年的情怀告诉[妈妈]41的冲动。于是，就有了这个梦。[每]44到春天，[我们]44的[这]43片小天地上，[迎春]45花唤醒万物，先是兰花和郁金香破土而出，继而杜鹃花含苞怒放，与满树的山茱萸花相映，深红的，淡紫的，鹅黄的，雪白的。就是那一天，[我]45梦见了，梦见了妈妈就在[这]43花丛中。
感觉结果还可以。明天开始写论文了 ^_^
2004年6月14日
The CR module
The most difficult module of my IRCRSystem was the CR module. And just now, I have solve it. I was so excited.
The CR module could add the suffix to each noun phrase. Based on the feature vector auto-extraction module. I had passed it.
Ok. Above all, I could display the final CR result by the txt format.
Tomorrow I could used the MFC to construct a beautiful interface. So terrific news for me. ^-^
This evening we had the final test of our English class. I had done my best.
Ok. Go back now, have a good rest and keep on my work for tomorrow.
The CR module could add the suffix to each noun phrase. Based on the feature vector auto-extraction module. I had passed it.
Ok. Above all, I could display the final CR result by the txt format.
Tomorrow I could used the MFC to construct a beautiful interface. So terrific news for me. ^-^
This evening we had the final test of our English class. I had done my best.
Ok. Go back now, have a good rest and keep on my work for tomorrow.
2004年6月13日
The feature vector auto-extraction
Yesterday I had finished the noun phrase recognization task. But I was confounded by the feature vector auto-extraction module. Because the considering cases were too many to clear up them. And at ten o'clock last evening, I decided to process it today.
This morning, before the lab weekly meeting, I began to analyze the feature vector auto-extraction module. After my carefully consideration, I thought there were three big cases. And in each big case there were three little cases. After all the cases working glibly in my brain, I was happy. I could solve it.
This afternoon, I began to code the cases. And just now I had finished this task and tested it. But when I began to design the coreference resolution module I found I must solve the suffix problem.
Ok. The idea was clearly. I could realize it tomorrow morning. But now it's time to do the evening practice: haveing some jogging. Go!
This morning, before the lab weekly meeting, I began to analyze the feature vector auto-extraction module. After my carefully consideration, I thought there were three big cases. And in each big case there were three little cases. After all the cases working glibly in my brain, I was happy. I could solve it.
This afternoon, I began to code the cases. And just now I had finished this task and tested it. But when I began to design the coreference resolution module I found I must solve the suffix problem.
Ok. The idea was clearly. I could realize it tomorrow morning. But now it's time to do the evening practice: haveing some jogging. Go!
2004年6月12日
The Noun Phrase Recognization
This was one big feaction of my CR system. Based on the name entity recognization task, I had done this task. The algorithm was same as the one in my CR paper.
But the feature vector extraction module was very complicated. I must clear up my thinking and relize it tomorrow.
Go and try!
But the feature vector extraction module was very complicated. I must clear up my thinking and relize it tomorrow.
Go and try!
2004年6月11日
Joshua Huang visits our lab
This afternoon, Dr.Joshua Huang visited our lab. He was the Assistant Director of the E-Business Technology Institute. He had many years experience in databases and data mining research in The Commonwealth Science and Industry Research Organization (CISRO), Australia.
After Dr.Tliu gave some introduce about our lab, he gave his introduce about his research and projects. I was interesting in his clustering algotithm based on K-NN. His idea was adding a variable w to restrict the weight of each variables when clustering. In his formula there was a variable beta that was the exponent of w. I found out in his ppt that he chose the beta factitiously. I saw he used 10, -9, -8 and -7 for beta. I asked him whether the beta could be modified heuristic or selfadapted. His answer was they had not done this deeply research.
He also gave us some analysis about the time serials predicting. He used the Multiple Regression Analysis for predicting. But as my experience I thought Multiple Regression Analysis could not give the proper curve trend.
Dr.Joshua Huang was good at data mining and business intelligence. I should study his research method and his paper on clustering.
After Dr.Tliu gave some introduce about our lab, he gave his introduce about his research and projects. I was interesting in his clustering algotithm based on K-NN. His idea was adding a variable w to restrict the weight of each variables when clustering. In his formula there was a variable beta that was the exponent of w. I found out in his ppt that he chose the beta factitiously. I saw he used 10, -9, -8 and -7 for beta. I asked him whether the beta could be modified heuristic or selfadapted. His answer was they had not done this deeply research.
He also gave us some analysis about the time serials predicting. He used the Multiple Regression Analysis for predicting. But as my experience I thought Multiple Regression Analysis could not give the proper curve trend.
Dr.Joshua Huang was good at data mining and business intelligence. I should study his research method and his paper on clustering.
2004年6月10日
The English oral test
This afternoon, all of our English students had the English oral test. The test content was based on the dialog of the appointed ten films. We had to pick one film. And our teacher picked stochasticly one snippet with some dialog. After the student watched the snippnet he must iterate the main idea.
I was the first one to have the test. I chose Krammer vs. Krammer. And I was appointed to listen the first snippnet. This snippnet was about Mr.Krammer talked to his boss in an office room. The time was thirty seconds. Frankly speaking, the speed was too fast. But as I had listened it many many times, I iterated it successfully. But I had one wrong pronunciation and with a little Chinese snippnet. I got 90%.
There was another exciting news that we could take part in the first mathemathcal modeling contest for graduate at Sep. 17. Just now I had trooped two of my best friends. We will struggle for it.
May us good luck!!
I was the first one to have the test. I chose Krammer vs. Krammer. And I was appointed to listen the first snippnet. This snippnet was about Mr.Krammer talked to his boss in an office room. The time was thirty seconds. Frankly speaking, the speed was too fast. But as I had listened it many many times, I iterated it successfully. But I had one wrong pronunciation and with a little Chinese snippnet. I got 90%.
There was another exciting news that we could take part in the first mathemathcal modeling contest for graduate at Sep. 17. Just now I had trooped two of my best friends. We will struggle for it.
May us good luck!!
2004年6月9日
Send my paper
This afternoon, I sent my paper Decision tree-based Chinese Noun Phrase Coreference Resolurion to the SWCL2004 webpage.
After the paper sent out I could finish next task that was building a coreference resolution system for any free text. This afternoon, I had built the preprocessing fraction including sentences dividing, word segment, pos tagging and name entity recognization. Then I would add my noun phrase recognization module into it. And finally I could separate the coreference resolution task as two parts: pronoun coreference resolution and general noun phrase coreference resolution. Based on the decision trees that of my finished tasks I could resolove them quickly.
Now the left tasks were only of programming. I should finish them quickly. Because the next task was writing my graduating design paper.
Let me try my best!
After the paper sent out I could finish next task that was building a coreference resolution system for any free text. This afternoon, I had built the preprocessing fraction including sentences dividing, word segment, pos tagging and name entity recognization. Then I would add my noun phrase recognization module into it. And finally I could separate the coreference resolution task as two parts: pronoun coreference resolution and general noun phrase coreference resolution. Based on the decision trees that of my finished tasks I could resolove them quickly.
Now the left tasks were only of programming. I should finish them quickly. Because the next task was writing my graduating design paper.
Let me try my best!
2004年6月8日
Paper's writing skill
Writing paper needs skill. I think so.
This morning, I invited Dr.Tliu, Mrs.Qinb, Carl and Lee as a committee to discuss my paper on Decision trees-based Chinese noun phrase coreference resolution. Before this committee, I had sent my paper to Mrs.Qin and Mr.Lu and got lots of useful suggestions. This morning we would discuss my third edition paper.
Dr.Tliu emphasized I must pay more attention on the basic concept and the title. Mrs.Qin gave me some advice about how to reduce the tables. Carl thought I could add some detailed information about the test result and the adventage about decision trees used for coreference resolution. Lee suggested me to modify the authors names in English.
Yes, there were some problems in my paper. And just now, I had modified them in my opinion.
There was somebody said that you would learn more after you modified some paper once. And I had felt it now. Thanks to the teachers and the studying brothers.
This morning, I invited Dr.Tliu, Mrs.Qinb, Carl and Lee as a committee to discuss my paper on Decision trees-based Chinese noun phrase coreference resolution. Before this committee, I had sent my paper to Mrs.Qin and Mr.Lu and got lots of useful suggestions. This morning we would discuss my third edition paper.
Dr.Tliu emphasized I must pay more attention on the basic concept and the title. Mrs.Qin gave me some advice about how to reduce the tables. Carl thought I could add some detailed information about the test result and the adventage about decision trees used for coreference resolution. Lee suggested me to modify the authors names in English.
Yes, there were some problems in my paper. And just now, I had modified them in my opinion.
There was somebody said that you would learn more after you modified some paper once. And I had felt it now. Thanks to the teachers and the studying brothers.
2004年6月7日
Can't forget this evening
This evening, after our English class, it was six o'clock, all of us came to KangLong Restaurant to have supper. This was the second class activity. All of us enjoyed ourself.
Can't forget this evening. Wang Shuting was very excited and said lots of words from her heart. Although there was not KalaOK, Jiang Wei and Lou Xiutao gave us wonderful songs. Although the time was not long, all of us said our words from heart.
This was the last class of our English class. I, as all of us, hoped we could keep our friendship for ever. I thought so.
Can't forget this evening. Wang Shuting was very excited and said lots of words from her heart. Although there was not KalaOK, Jiang Wei and Lou Xiutao gave us wonderful songs. Although the time was not long, all of us said our words from heart.
This was the last class of our English class. I, as all of us, hoped we could keep our friendship for ever. I thought so.
2004年6月6日
Doing some exercise is a good habit
Yes, just like the caption, I think so.
When I was in high school, I, with my roomates, was forced to do morning exercise. That three years process I had kept the habit of doing morning exercise.
And when I was in the first two years in campus life, I kept this habit. But when I came into the last two years of my campus life, I had little time to do morning exercise.
Recently, after ten o'clock every evening I, with my roomates, did evening exercise. The exercise content included middle-distance race and playing basketball. Right now, I can obviously find out that my body condition has recovered.
Change the time to do exercise. This is a nice way for me.
When I was in high school, I, with my roomates, was forced to do morning exercise. That three years process I had kept the habit of doing morning exercise.
And when I was in the first two years in campus life, I kept this habit. But when I came into the last two years of my campus life, I had little time to do morning exercise.
Recently, after ten o'clock every evening I, with my roomates, did evening exercise. The exercise content included middle-distance race and playing basketball. Right now, I can obviously find out that my body condition has recovered.
Change the time to do exercise. This is a nice way for me.
2004年6月5日
The 2rd edition of my paper
I thought writing paper was a process of updating the editions of your paper.
Based on the first edition's suggestion from Mrs.Qin and Mr.Lu, I added some new understanding to the new edition.
This was my first chance of writing paper about NLP. So some problems had displayed. For example, I would like to explain some concept in words, but sometimes the better way was using some figures or tables.
Just now I had sent my 2rd paper to some teachers and some learning brothers. I hoped I can get some modifying suggestions.
Based on the first edition's suggestion from Mrs.Qin and Mr.Lu, I added some new understanding to the new edition.
This was my first chance of writing paper about NLP. So some problems had displayed. For example, I would like to explain some concept in words, but sometimes the better way was using some figures or tables.
Just now I had sent my 2rd paper to some teachers and some learning brothers. I hoped I can get some modifying suggestions.
2004年6月4日
Xiangyang Shen visit our lab
This afternoon, the new president of MSRA Xiangyang Shen visited our lab. Like Yaqin Zhang, he was also in high spirits.
And Dr.Tliu gave us a exciting news that our lab was one of the union labs with MSRA. So after now, we will begin to cooperate with MSRA. So excited news.
And Dr.Tliu gave us a exciting news that our lab was one of the union labs with MSRA. So after now, we will begin to cooperate with MSRA. So excited news.
2004年6月3日
Finish my primary paper
This morning I finished my primary paper for SWCL2004. It was named as Design tree-based Chinese Noun Phrase COreference Resolution. I sent it to Mrs.Qin for some modifying suggestion.
After I came back from the English class. I receieved Mrs.Qin's modifying suggestion. She thought I could introduce firstly the basic concept about coreference resolution before coreference resolution for noun phrase. And I should introduce some detail information about the other methods about the rule-based for coreference resolution. The results displayed of NP identify module were too many. Whether did the training samples fit for the truth?
So many problems in my paper. I would modify them tomorrow.
Ok. Come back for jog with my roomates.
After I came back from the English class. I receieved Mrs.Qin's modifying suggestion. She thought I could introduce firstly the basic concept about coreference resolution before coreference resolution for noun phrase. And I should introduce some detail information about the other methods about the rule-based for coreference resolution. The results displayed of NP identify module were too many. Whether did the training samples fit for the truth?
So many problems in my paper. I would modify them tomorrow.
Ok. Come back for jog with my roomates.
2004年6月2日
Sports Season
I obversily fell that the sports season had come following the sunny days weather. Many classmates of my English class told they wanted to have some sports in these days. And this noon Mr. Anson, Zsq, Taozi, and me came to play table tennis. After I have being done this diary, I must come back to my dorm to have some jog with my roomates.
So good. Sport is the power of each body.
Ok. Come back now.
So good. Sport is the power of each body.
Ok. Come back now.
2004年6月1日
Table tennis vs. disengaged life
This evening, I played table tennis with one of my English classmates. He fell very disengaged. As he had finish his graduating design and his future research content was not related with his recent direction.
He said that his life was very comfortable and after these days we could not have the days like them. And he would adjust his life to make his great effort to complete his dream.
May good wish to him!
Change vies to myself. Just now I have found the Special issue on computational anaphora resolution. I would do more on this topic.
Try try and try!!
He said that his life was very comfortable and after these days we could not have the days like them. And he would adjust his life to make his great effort to complete his dream.
May good wish to him!
Change vies to myself. Just now I have found the Special issue on computational anaphora resolution. I would do more on this topic.
Try try and try!!
订阅：
博文 (Atom)