Turkish and Azerbaijani/Final report - Revision history

Francis Tyers: /* Statistics */

2011-08-25T18:40:56Z

Statistics

Zfe: /* Statistics */

2011-08-25T18:39:27Z

Statistics

Zfe: /* Statistics */

2011-08-25T18:35:36Z

Statistics

Zfe: /* Statistics */

2011-08-25T18:32:42Z

Statistics

Francis Tyers: /* See also */

2011-08-25T17:49:58Z

Francis Tyers: /* Statistics */

2011-08-25T17:45:07Z

Statistics

Francis Tyers: /* See also */

2011-08-25T17:44:17Z

Zfe: /* See also */

2011-08-25T17:41:40Z

78.160.82.153: /* Statistics */

2011-08-25T17:39:58Z

Statistics

193.205.136.3: /* What I am happy with */

2011-08-25T09:38:08Z

What I am happy with

@@ Line 36: / Line 36: @@
 ; Dictionaries
-* azmorph lexicon: 7375
+* Azmorph lexicon: 7,375
-* trmorph lexicon: 7970
+* Trmorph lexicon: 7,970
-* tr-az bidix: 8208
+* tr-az bidix: 8,208
 ; Coverage
-* Turkish Wikipedia:70.983710268250007 +/- 4.6352598044670
+* Turkish Wikipedia: 70.9 +/- 4.6352598044670
-* Turkish SETimes: 84.84591576 +/- 0.568940593619
+* Turkish SETimes: 84.8 +/- 0.568940593619
 ; Rules
+* Constraint grammar (disambiguation) rules: 114
+* Transfer rules: 4
-; Constraint grammar rules
 ; Error rate

@@ Line 47: / Line 47: @@
 ; Rules
-...
+; Constraint grammar rules
 ; Error rate

@@ Line 60: / Line 60: @@
 | <code>setimes.bulgar.tr.txt</code> || 395 || - || - || - || - || -
 |-
-| <code>wikipedia.kadinlar_askerler.tr.txt</code> || 1165 || - || 22.89 || 22.31 || - || -
+| <code>wikipedia.kadinlar_askerler.tr.txt</code> || 1165 || 10.79 || 22.89 || 22.31 || - || -
 |-
 |}

@@ Line 60: / Line 60: @@
 | <code>setimes.bulgar.tr.txt</code> || 395 || - || - || - || - || -
 |-
-| <code>wikipedia.kadinlar_askerler.tr.txt</code> || 1165 || - || - || - || - || -
+| <code>wikipedia.kadinlar_askerler.tr.txt</code> || 1165 || - || 22.89 || 22.31 || - || -
 |-
 |}

← Older revision		Revision as of 17:49, 25 August 2011
Line 70:		Line 70:
	==See also==		==See also==

	* [[User:Zfe/Application]]] -- Original application		* [[User:Zfe/Application]] -- Original application

← Older revision		Revision as of 17:44, 25 August 2011
Line 70:		Line 70:
	==See also==		==See also==

	* ~~http://wiki.apertium.org/wiki/~~User:Zfe/Application		* [[User:Zfe/Application]]] -- Original application

@@ Line 70: / Line 70: @@
 ==See also==
+* http://wiki.apertium.org/wiki/User:Zfe/Application
-* ''link to original proposal''

@@ Line 42: / Line 42: @@
 ; Coverage
-* Turkish Wikipedia ( , std. dev.: )
+* Turkish Wikipedia ( , std. dev.: ) 70.983710268250007 +/- 4.6352598044670
 * Turkish SETimes ( , std. dev.: ) 84.84591576 +/- 0.568940593619

@@ Line 12: / Line 12: @@
 . The team: it seems that we could manage to get a team of knowledgeable people to fix most of the issues. Pros about the team: nobody knows turkish well but we are all able to reason over it and find better solutions and categorisations than OHOHIHAVEAPHDINTURKISHLINGUISTICS people. (Yes, i'm talking of the people who wrote the infamous Routledge Comprehensive Grammar of Turkish).
-Another point that should probably be investigated is how beneficial variety in the group is to the project. Our group was quite mixed (we had in fact an engineer, a linguist and a nothing -me-) and we had, almost daily, bits of the eternal struggle between sein and sollen, with the linguist playing the part of the guy who always wanted to do things "in the right way" and the software developer playing the "the way it will work sooner" part. I was in the middle of the struggle and my initial position, which was more on the linguistics side of struggle, shifted towards the necessity of doing something that works. When somebody changes his point of view I think we can safely say that the discussion has been productive.
+Another point that should probably be investigated is how beneficial variety in the group is to the project. Our group was quite mixed (we had in fact a developer, a linguist and a nothing -me-) and we had, almost daily, bits of the eternal struggle between sein and sollen, with the linguist playing the part of the guy who always wanted to do things "in the right way" and the software developer playing the "the way it will work sooner" part. I was in the middle of the struggle and my initial position, which was more on the linguistics side of struggle, shifted towards the necessity of doing something that works. When somebody changes somebody's point of view I think we can safely say that the discussion has been productive.
 . CG: Yes, the CG is not that good. The point is that the lexicon contained in TRmorph is horrible and hence it makes the disambiguation hard, if not impossible. Our CG set is pretty basic and messy, nonetheless it serves the purpose quite well. There are known issues with disambiguating turkish using a CG, we are aware of that. We plan to add a more sophisticated CG in the next months. Having ~80% of words translated well, with most of 20% of mistakes consisting of azmorph wrong morphology makes me think that the CG works quite well, given that in some cases a wrong disambiguation is not that detrimental to the translation, since we usually get many free rides, given the fact that Turkish and Azeri are really closely related languages.