User:Linh le/2014Application - Revision history

Linh le: Blanked the page

2014-04-28T14:25:36Z

Blanked the page

Show changes

Linh le: /* Week 4 (June 8-15) */

2014-03-21T16:04:33Z

Week 4 (June 8-15)

Linh le: /* How and who it will benefit in the society */

2014-03-21T16:03:58Z

How and who it will benefit in the society

Linh le: /* Why Google and Apertium should sponsor it */

2014-03-21T16:02:53Z

Why Google and Apertium should sponsor it

Linh le: /* Week 4 (June 8-15) */

2014-03-21T14:34:13Z

Week 4 (June 8-15)

Linh le at 14:31, 21 March 2014

2014-03-21T14:31:29Z

Linh le: /* Non-GSOC schedule */

2014-03-21T14:27:02Z

Non-GSOC schedule

Linh le: /* Week 12 (August 3-9) */

2014-03-21T14:22:32Z

Week 12 (August 3-9)

Linh le: /* Week 9 (July 14-20) */

2014-03-21T14:21:28Z

Week 9 (July 14-20)

Linh le: /* Week 8 (July 7-13) */

2014-03-21T14:20:43Z

Week 8 (July 7-13)

@@ Line 67: / Line 67: @@
 * (If possible) 200-word corpus test (coverage 60%)
-====== Week 4 (June 8-15) ======
+====== Week 4 (June 9-15) ======
 * 200-word corpus test
 * Add transfer rules

@@ Line 31: / Line 31: @@
 ==== How and who it will benefit in the society ====
-Vietnamese speakers, especially monolingual speakers, will benefit. That is to say, at least 80 millions people. As stated above, studying a language is costly in terms of time and money, and a MT is a feasible alternative, since more and more people these days are also getting access to the Internet. With this machine, reading of news, documents as well as exchanging of ideas will be made easier for Vietnamese who hope to interact more with people from other countries, and the MT will also open a bigger door for non-Vietnamese speakers who hope to learn more about the language as well as the country.
+Vietnamese speakers, especially monolingual speakers, will benefit. That is to say, at least 80 millions people. As stated above, studying a language is costly in terms of time and money, and a MT is a feasible alternative, since more and more people these days are also getting access to the Internet. With this machine, reading of news, documents as well as exchanging of ideas will be made easier for Vietnamese speakers who hope to interact more with people from other countries, and the MT will also open a bigger door for non-Vietnamese speakers who hope to learn more about the language as well as the country.
 ==== Work plan ====

@@ Line 24: / Line 24: @@
 ==== Adopting unreleased Vietnamese-English pair and bringing it to release quality ====
 ==== Why Google and Apertium should sponsor it ====
-Although Vietnamese is spoken by around 80 million people as their first language in Vietnam, as well as other millions of people in the US, Australia, Canada, Germany and so on, there is not much work in progress supporting the translation of Vietnamese to other languages. On Apertium, the pair vi-en currently is also in the incubator, not having developed much.
+Although Vietnamese is spoken by around 80 million people as their first language in Vietnam, as well as other millions of people in the US, Australia, Canada, Germany and so on, there is not much work in progress supporting the translation of Vietnamese to other languages. On Apertium, the pair vi-en currently is also in the incubator, not having been developed much.
-A part of the Austroasiatic family, Vietnamese is considered to be closely related to some languages and dialects spoken in Cambodia, Thai, Laos, India, Bangladesh. In addition, having been under Chinese occupation for centuries, the language is also much similar to Cantonese in sounds and grammar. Therefore, the rules created from this project can be useful for some other dialects , especially ones that are less often represented.
+A part of the Austroasiatic family, Vietnamese is considered to be closely related to some languages and dialects spoken in Cambodia, Thai, Laos, India, Bangladesh. In addition, having been under Chinese occupation for centuries, the language also bears similarities to  Cantonese in terms of sounds and grammar. Therefore, the rules created from this project can be useful for some other dialects , especially ones that are less often represented.
-I'm aware that there are other MT available for Vietnamese-English translation (Microsoft, Google, and one by a Vietnamese company that is very slow and only works for short sentences), among which Google Translation seems to be the best one. I have only been able to manually test these machines, and found that while Google's coverage is great for monosyllabic words, many bi- or polysyllabic words that make up a large part of Vietnamese are not recognized and translated as monosyllables, making little sense. In addition, the grammar and lexical selection of the system also seem to require much more work. I understand that it is impossible to create a fluent translation system in three months, but it should be enough to create a good framework for future continuing development.
+I'm aware that there are other MT available for Vietnamese-English translation (Microsoft, Google, and one by a Vietnamese company that is very slow and only works for short sentences), among which Google Translation seems to be the best one. I have only been able to manually test these machines, and found that while Google's coverage is great for monosyllabic words, many bi- or polysyllabic words that make up a large part of Vietnamese are not recognized and translated as monosyllables, making little sense. In addition, the grammar and lexical selection of the system also seem to require more work. I understand that it is impossible to create a fluent translation system in three months, but it should be enough to create a good framework for future continuing development.
 ==== How and who it will benefit in the society ====

@@ Line 72: / Line 72: @@
 * 4800 words in dix
 * Expand bilingual dix
+* Clean testvoc
 * Document
-'''''Deliverable: 2 monolingual dix and bilingual dix, WER 20%, naive bidix-trimmed coverage 60-70% clean testvoc for <n> <qnt>, <num>, articles,interjection'''''
+'''''Deliverable: 2 monolingual dix and bilingual dix, WER 20%, naive bidix-trimmed coverage 60-70% testvoc clean for <n> <qnt>, <num>, articles,interjection'''''
 ====== Week 5 (June 16-22) ======

@@ Line 13: / Line 13: @@
 == Why are you interested in Apertium project? ==
-First of all, since Apertium is an open-source project, everyone can contribute and I think that this system is perfect for language translation. Since languages are created, developed, modified, and used by people, they require human involvement and interactions, and therefore it's great for many people to work together on one project. In addition, the platform is also very open, in that people of various backgrounds and experiences can join and contribute (which is the reason why I want to do so as well).  <br>
+First of all, since Apertium is an open-source project, everyone can contribute and I think that this system is perfect for language translation. Since languages are created, developed, modified, and used by people, they require human involvement and interactions, and therefore it is great for many people to work together on one project. In addition, the platform is also very open, in that people of various backgrounds and experiences can join and contribute (which is the reason why I want to do so as well).  <br>
 Second, despite having no immediate relations, there are many similarities in the grammar structures of the specific pair of languages that I'm thinking about (Vietnamese<->English), and therefore I believe that the rule-based MT Apertium can provide a great system for translation between this pair.<br>
@@ Line 24: / Line 24: @@
 ==== Adopting unreleased Vietnamese-English pair and bringing it to release quality ====
 ==== Why Google and Apertium should sponsor it ====
-Although Vietnamese is spoken by around 80 million people as their first language in Vietnam, as well as other millions of people in the US, Australia, Canada, Germany and so on, there is not much work in progress on supporting the translation of Vietnamese to other languages. On Apertium, the pair vi-en currently is also in the incubator, not having developed much.
+Although Vietnamese is spoken by around 80 million people as their first language in Vietnam, as well as other millions of people in the US, Australia, Canada, Germany and so on, there is not much work in progress supporting the translation of Vietnamese to other languages. On Apertium, the pair vi-en currently is also in the incubator, not having developed much.
 A part of the Austroasiatic family, Vietnamese is considered to be closely related to some languages and dialects spoken in Cambodia, Thai, Laos, India, Bangladesh. In addition, having been under Chinese occupation for centuries, the language is also much similar to Cantonese in sounds and grammar. Therefore, the rules created from this project can be useful for some other dialects , especially ones that are less often represented.
-I'm aware that there are other MT available for Vietnamese-English translation (Microsoft, Google, and one by a Vietnamese company that is very slow and only works for short sentences), among which Google Translation seems to be the best one. I have only been able to manually test these machines, and found that while Google's coverage is great for monosyllabic words, many bi- or polysyllabic words that make up a large part of Vietnamese are not recognized and translated as monosyllables, making little sense. In addition, the grammar and lexical selection of the system also seem to require much more work. I understand that it's impossible to create a fluent translation system in three months, but it should be enough to create a good framework for future continuing development.
+I'm aware that there are other MT available for Vietnamese-English translation (Microsoft, Google, and one by a Vietnamese company that is very slow and only works for short sentences), among which Google Translation seems to be the best one. I have only been able to manually test these machines, and found that while Google's coverage is great for monosyllabic words, many bi- or polysyllabic words that make up a large part of Vietnamese are not recognized and translated as monosyllables, making little sense. In addition, the grammar and lexical selection of the system also seem to require much more work. I understand that it is impossible to create a fluent translation system in three months, but it should be enough to create a good framework for future continuing development.
 ==== How and who it will benefit in the society ====
@@ Line 39: / Line 39: @@
 ====== Bonding period ======
-* Continue working on the coding challenge (if it hasn't been completed).
+* Continue working on the coding challenge (if not yet completed).
 * Get familiar:
 ** Be on IRC often and get used to the community
@@ Line 135: / Line 135: @@
 ==== List your skills and give evidence of your qualifications ====
-I'm a junior at Smith College, USA but Computer Science experience-wise, I'm a sophomore. I've had experience coding in Python, Java, with a summer working on CSS and Artificial Intelligence. I've been learning Japanese in the two years I have been in America, and one year in Japan (currently). Apertium is my first open source project, but it's been nice so far, and I will definitely continue contributing.
+I am a junior at Smith College, USA but Computer Science experience-wise, I am a sophomore. I have had experience coding in Python, Java, with a summer working on CSS and Artificial Intelligence. I have been learning Japanese in the two years I have been in America, and one year in Japan (currently). Apertium is my first open source project, but it has been nice so far, and I will definitely continue contributing.
-I'm a native Vietnamese speaker, and is a student in an American college and have been using English as the main language of communication for the last 3 and a half years. Before going to America 4 years ago, I have studied English for 5 years.
+I am a native Vietnamese speaker, and is a student in an American college and have been using English as the main language of communication for the last 4 years (I take classes in both Japanese and English in Japan). Before going to America 4 years ago, I have studied English for 5 years.
 ==== Non-GSOC schedule ====
-I'm considering taking a CS class but it will become 2nd priority if I get accepted and I will discuss with my mentor before I decide to take  it. Other than that, I do not have any plans for the summer, and I am willing to spend 40 hours a week on Apertium because I think that is the time I will need to complete my goals.
+I'm considering taking a CS class but it will become 2nd priority if I get accepted and I will discuss that with my mentor before I make any decision. Other than that, I do not have any plans for the summer, and I am willing to spend 40 hours a week on Apertium because I think that is the time I will need to complete my goals.

← Older revision		Revision as of 14:27, 21 March 2014
Line 140:		Line 140:

	==== Non-GSOC schedule ====		==== Non-GSOC schedule ====
	I ~~don~~'t have any ~~other~~ plans for the summer, and I'm willing to spend 40 hours a week on Apertium because I think that ~~that's~~ the time I will need to complete my goals.		I'm considering taking a CS class but it will become 2nd priority if I get accepted and I will discuss with my mentor before I decide to take it. Other than that, I do not have any plans for the summer, and I am willing to spend 40 hours a week on Apertium because I think that is the time I will need to complete my goals.

@@ Line 125: / Line 125: @@
 ====== Week 12 (August 3-9) ======
-* 500-word corpus test (coverage 80-90%)
+* 500-word corpus test
 * 8500 words in dix

@@ Line 110: / Line 110: @@
 * Training of Vietnamese tagger
 * 6725 words in dix
-* 500-word corpus test (coverage 70-80%, WER 30-40% - but higher than previous result)
+* 500-word corpus test
 * Regression testing

@@ Line 105: / Line 105: @@
 * Document
-'''''Deliverable: ,coverage 70-80%, WER 20-30%, testvoc clean for <v>, <cnjcoo>, <cnjsub> '''''
+'''''Deliverable: coverage 70-80%, WER 20-30%, testvoc clean for <v>, <cnjcoo>, <cnjsub> '''''
 ====== Week 9 (July 14-20) ======