User:Mathematic-alpha/proposal - Revision history

Mathematic-alpha at 20:32, 11 May 2019

2019-05-11T20:32:36Z

Mathematic-alpha: /* Major goals */

2019-04-15T00:26:46Z

Major goals

Firespeaker: /* Major goals */

2019-04-12T21:12:03Z

Major goals

Mathematic-alpha: /* Workplan */

2019-04-08T21:00:26Z

Workplan

Mathematic-alpha: /* Major goals */

2019-04-08T20:57:15Z

Major goals

Mathematic-alpha: /* Major goals */

2019-04-08T20:55:57Z

Major goals

Firespeaker: /* Major goals */

2019-04-07T13:13:52Z

Major goals

Firespeaker: /* Workplan */

2019-04-07T13:12:31Z

Workplan

Mathematic-alpha at 12:45, 7 April 2019

2019-04-07T12:45:53Z

Mathematic-alpha at 12:33, 7 April 2019

2019-04-07T12:33:02Z

@@ Line 1: / Line 1: @@
+== Information ==
+This project was accepted for the 2019 edition of Google Summer of Code.
+Consider checking [http://wiki.apertium.org/wiki/User:Mathematic-alpha/gsoc-progress this page] to check on the progress of the work.
+Thanks
 == Contact Information ==

@@ Line 56: / Line 56: @@
 {{comment|Yes since I have worked on it in GCI. I can still bootstrap a new pair if it is imperative  —[[User:Mathematic-alpha|Mathematic-alpha]] ([[User talk:Mathematic-alpha|talk]]) 21:55, 8 April 2019 (CEST)}}
 {{comment|:Bootstrapping a new pair isn't useful if one already exists, but the coding challenge is indeed imperative! —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 23:12, 12 April 2019 (CEST)}}
+{{comment| Noted}}
 *Developing a minimal interface for adding words and transfer rules

@@ Line 55: / Line 55: @@
 {{comment|Yes since I have worked on it in GCI. I can still bootstrap a new pair if it is imperative  —[[User:Mathematic-alpha|Mathematic-alpha]] ([[User talk:Mathematic-alpha|talk]]) 21:55, 8 April 2019 (CEST)}}
+{{comment|:Bootstrapping a new pair isn't useful if one already exists, but the coding challenge is indeed imperative! —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 23:12, 12 April 2019 (CEST)}}
 *Developing a minimal interface for adding words and transfer rules

@@ Line 164: / Line 164: @@
 | style="text-align:center" | ~18,500
 | style="text-align:center" | (WP) 6,6%
-| style="text-align:center" | ~89.5%
+| style="text-align:center" | ~92.0%
 |-
 ! 11
@@ Line 171: / Line 171: @@
 | style="text-align:center" | ~19,500
 | style="text-align:center" | fra>byv (WP) 15,0%
-| style="text-align:center" | ~90%
+| style="text-align:center" | ~93.0%
 |-
 ! 12
@@ Line 186: / Line 186: @@
 | style="text-align:center" | ~19,500
 | style="text-align:center" | <15%
-| style="text-align:center" | ~90.5%
+| style="text-align:center" | ~93.5%
 |}
 {{comment|Why does coverage go down in some cases? —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 15:12, 7 April 2019 (CEST)}}
+{{comment|Mistake. I am sorry —[[User:Mathematic-alpha|Mathematic-alpha]] ([[User talk:Mathematic-alpha|talk]]) 21:59, 8 April 2019 (CEST)}}
 === List your skills and give evidence of your qualifications ===

@@ Line 54: / Line 54: @@
 {{comment|Do you have a coding challenge related to this pair? That would be very important. —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 15:13, 7 April 2019 (CEST)}}
-{{comment|Yes since I have worked on it in GCI. I can still bootstrap a new pair if it is imperative  —[[User:Mathematic-alpa|Mathematic-alpa]] ([[User talk:Mathematic-alpa|talk]]) 21:55, 8 April 2019 (CEST)}}
+{{comment|Yes since I have worked on it in GCI. I can still bootstrap a new pair if it is imperative  —[[User:Mathematic-alpha|Mathematic-alpha]] ([[User talk:Mathematic-alpha|talk]]) 21:55, 8 April 2019 (CEST)}}
 *Developing a minimal interface for adding words and transfer rules
@@ Line 61: / Line 61: @@
 ** Interface for adding transfer rules
-The rationale for proposing a GUI is to encourage more people to get involved since most people i meet are not very comfortable with terminal and all the rest.
+The rationale for proposing a GUI is to encourage more people to get involved since most people I meet are not very comfortable with the terminal and all the rest.
-During the post-application period, I plan to study in more detail the apertium-ambiguous package. I will also learn more about developing applications on the GitHub platform. My current perception is that for the limited time of the GSoC it is better to invest in developing what might serve as basis to bring more non-technical contributors while showing a case study.
+During the post-application period, I plan to study in more detail the apertium-ambiguous package. I will also learn more about developing applications on the GitHub platform. My current perception is that for the limited time of the GSoC it is better to invest in developing what might serve as a basis to bring more non-technical contributors while showing a case study.
 === Reasons why Google and Apertium should sponsor it ===

@@ Line 52: / Line 52: @@
 **Mə̀dʉ̂mbɑ̀ to Français
 **Français to Mə̀dʉ̂mbɑ̀
+{{comment|Do you have a coding challenge related to this pair? That would be very important. —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 15:13, 7 April 2019 (CEST)}}
 *Developing a minimal interface for adding words and transfer rules
 ** Demo https://github.com/math-alpha/contribution

@@ Line 192: / Line 192: @@
 I’ve been working on Apertium since 2016 though there have been times of break due to school. In 2016 I created the Mə̀dʉ̂mbɑ̀-French pair which I worked on during GCI 2016 (I was selected as a finalist). I’ve mentored and was strongly involved in the 2018 edition of GCI.
-Catalan is my mother tongue, and I’ve been studying it at the university. I'm a fluent speaker of Spanish and French. I read fluently in Italian and Portuguese, among other Romance languages, but my knowledge of them is mainly passive and linguistic. That’s why I’ll work mainly translating from Italian and Portuguese into Catalan, but my knowledge of Italian is good enough to create the first version of a translator from Catalan to Italian.
 == List any non-Summer-of-Code plans you have for the Summer ==

@@ Line 53: / Line 53: @@
 **Français to Mə̀dʉ̂mbɑ̀
 *Developing a minimal interface for adding words and transfer rules
+** Demo https://github.com/math-alpha/contribution
+** Interface for adding words
+** Interface for adding transfer rules
+The rationale for proposing a GUI is to encourage more people to get involved since most people i meet are not very comfortable with terminal and all the rest.
-Unlike it happens with French, compared to other Romance languages, there are not big structural (syntax) differences between Catalan, Italian and Portuguese. If we improve the morphological disambiguation, add several thousands of words in the dictionaries, introduce lexical selection rules and create some more transfer rules, a low WER can be reached.
-During the post-application period I plan to study in more detail the apertium-ambiguous package. Nevertheless as syntax in the three languages is practically the same, I think it would be useful only for introducing phrases. For the same reason, I do not think that apertium-separator would help here (unless it is indeed helpful for e.g. the French-Catalan pair). My current perception is that for the limited time of the GSoC it is better to invest in the expansion of dictionaries, the improvement of morphological disambiguation (especially for Portuguese, but also for Italian) and the introduction of a few more structural transfer rules. In any case I am totally open to suggestions and will be happy to try new modules if my potential mentors consider it preferable.
+During the post-application period, I plan to study in more detail the apertium-ambiguous package. I will also learn more about developing applications on the GitHub platform. My current perception is that for the limited time of the GSoC it is better to invest in developing what might serve as basis to bring more non-technical contributors while showing a case study.
 === Reasons why Google and Apertium should sponsor it ===
@@ Line 62: / Line 65: @@
 As mentioned above, the Apertium community is strongly committed to under-resourced and minoritised/marginalised languages and Google helps its own way via programs like GSoC and GCI.
 There exist many local cultural movements in Africa with the goal of developing language and opening to the world but they generally fail to duel on a scientific basis. This project will definitely mark a starting point or proof of concept in Machine Translation in Cameroon and will greatly have a positive impact on language development.
-==== Italian to Catalan ====
-*bidix: 9091 pairs (excluding proper names)
-*Coverage: 81.7% (calculated using a Wikipedia corpus with 3.0 M words)
-*Word error rate (WER): 30.0% (calculated using random Wikipedia texts with a total of 933 words)
-*Word error rate (WER) using Google Translator: 14.0% (calculated using the same test text)
-==== Portuguese to Catalan ====
-*bidix: 7576 pairs (excluding proper names)
-*Coverage: 84.4% (calculated using a Wikipedia corpus with 3.1 M words)
-*Word error rate (WER): 28.4% (calculated using random Wikipedia texts with a total of 1648 words)
-*Word error rate (WER) using Google Translator: 21.6% (calculated using the same test text)
-==== Catalan to Portuguese ====
-*bidix: 7576 pairs (excluding proper names)
-*coverage: 87.6% (calculated using a Wikipedia corpus with 2.6 million words)
-==== apertium-por ====
-*There is not any released language pair working with apertium-por.
-*There is a basic morphological disambiguation using CG, but less developed than in apertium-cat, apertium-spa and apertium-fra.
-*The dictionary has mainly old-fashioned paradigms for proper names:
-**it uses "loc" instead of "top"
-**proper names do not have gender and number
-**there are a few "cog", but most of them are defined as "ant"
-According to my experience, the improvement of the proper names according to the current paradigms style for proper names improves significantly the results in the translations between Romance languages in Wikipedia texts, where they are very numerous. This was a important part of the 2017 English-Catalan GSoC project, and the word lists then created by Marc Riera would help a lot the work for the Portuguese dictionary, where there are only a bit more of 2,000 proper names.
 === Online translations ===
@@ Line 207: / Line 184: @@
 | style="text-align:center" | ~90.5%
 |}
-{|class=wikitable
-! Setmana !! Dates                !!  Descripció !!  Bidix<br/>(sense np)<br/>previst !!(%) Cobertura<br/>prevista !! (%) WER<br/>previst !! Testvoc  !! Avaluació !! Bidix<br/>real !! (%) Cobertura<br/>real !! (%) WER !! Err. !! Fet?
-|-
-| 0      || <b>français > occitan</b> ||                  ||    ~5 700       ||          ||         ||   ||        ||    ||    || ||   ||
-|-
-| 1      || 14 mai&mdash;20 mai  || Improving Occitan monodix<br/>Adding prn, pr, cnj*, basic adv to bidix ||    ~6,000       ||  ~84,0%  ||         ||  ||        || 7643 || 77,1%   || ||   || ½
-|-
-| 2      || 21 mai&mdash;27 mai  || Adding n, adj, adv to the bidix from the French dictionary ||    ~12,000       ||  ~86,0%  ||         ||  ||        || 12811 || 82,2% || ||   || ½
-|-
-| 3      || 28 mai&mdash;3 junh || Adding vblex to the bidix from the French Wictionary<br/>Beginning to add missing words in decreasing order of frequency fra > oci ||    ~14,000       ||  ~88.0%  ||         ||  ||        || 14452   || 85,1% || ||   || ½
-|-
-| 4      || 4 junh&mdash;10 junh || Adding words<br/>Transfer rules fra > oci ||  ~16,000       ||  ~89.0%  ||         ||  ||        || 16745  ||  89,2%  || ||   || ✓
-|-
-| 5     || <b>11 junh&mdash;15 junh<br>Deliverable #1: French to Occitan translator</b> || Adding words<br/>Transfer rules fra > oci ||  <b>~18,000</b>       ||  <b>~89.5%</b>  ||  <b>~25%</b>   ||  ||    || 19897 || 91,1% || (WP) 15,0% ||  ||  ✓
-|-
-| 6    || 18 junh&mdash;24 junh || Adding words<br/>Transfer rules fra > oci<br/>Begin testvoc fra > oci ||  ~20,000       ||  ~90.0%  ||         ||  pr, cnj*, adv, prn, det || || 20581 || 91,5% || (WP) 12,3% || 0  || ✓
-|-
-| 7  || 25 junh&mdash;1 julhet || Adding words<br/>Transfer rules fra > oci<br/>Testvoc fra > oci ||  ~21,000       ||  ~90.5%  ||         ||  vblex    ||    || 21823 || 91,8% || (Euro- News) 18,0% || 0 || ✓
-|-
-| 8  || 2 julhet&mdash;8 julhet || Adding words<br/>Transfer rules fra > oci<br/>Testvoc fra > oci ||  ~22,000       ||  ~91.0%  ||         ||  adj     ||    ||  22609 ||  91,9% ||   || 0 || ✓
-|-
-| 9  || <b>9 julhet&mdash;13 julhet<br>Deliverable #2: French to Occitan translator</b> || Transfer rules fra > oci<br/>Testvoc fra > oci ||  <b>~22,000</b>     ||  <b>~91.0%</b>  ||  <b>~15%</b>   ||  n        ||    || 25045   || 92,1% || (WP) 7,2% || 0 || ✓
-|-
-| 0  || <b>occitan > français</b> ||  ||    ~22,000       ||          ||         ||   ||        ||    ||    || ||   ||
-|-
-| 10   || 16 julhet&mdash;22 julhet || Adding  missing words in decreasing order of frequency oci > fra<br/>Transfer rules oci > fra<br/>Testvoc oci > fra ||   ~22,500      ||  ~88.0%  ||       || pr, cnj*, adv, prn, det ||    || 25161 || 91,7% || fra>oci (Euro- News) 6,6% || 10  || ✓
-|-
-| 13   || 23 julhet&mdash;29 julhet || Adding words<br/>Transfer rules oci > fra <br/>Testvoc oci > fra ||   ~23,000      ||  ~89.0%   ||       || n, adj ||    || 25504 || 92,1% ||   || 1 || ✓
-|-
-| 11    || 30 julhet&mdash;5 agost || Adding words<br/>Transfer rules oci > fra <br/>Testvoc oci > fra ||   ~23,500      ||  ~90.0% ||         || vblex ||    || 26908 || oci>fra 92,9% fra>oci 92,3% || fra>oci (WP) 10,0% || 0 || ½
-|-
-| 12*   || 6 agost&mdash;9 agost || Final improvements ||         ||    ||     || ||    ||    || ||   ||   ||
-|-
-| 12**   || <b>10 agost&mdash;14 agost<br>Deliverable #3: Occitan to French translator</b> || Final evalution|| <b>~23,500</b>  || <b>~90.0%</b> ||  <b>~30%</b>   ||             ||    ||    || ||   ||   ||
-|-
-|}
 === List your skills and give evidence of your qualifications ===