Difference between revisions of "Hectoralos/GSOC 2019 work plan control"

From Apertium
Jump to navigation Jump to search
 
(26 intermediate revisions by the same user not shown)
Line 2: Line 2:
   
 
{|class="wikitable"
 
{|class="wikitable"
! style="width: 10%" rowspan=2 | Week
+
! style="width: 6%" rowspan=2 | Week
! style="width: 15%" rowspan=2 | Dates
+
! style="width: 10%" rowspan=2 | Dates
 
! colspan=4 | Goals
 
! colspan=4 | Goals
 
! colspan=5 | Fulfilled
 
! colspan=5 | Fulfilled
 
|-
 
|-
! style="width: 13%" | Bidix<br>(excluding<br>proper names)
+
! style="width: 8%" | Bidix<br>(excluding<br>proper names)
! style="width: 13%" | WER
+
! style="width: 8%" | WER
! style="width: 13%" | Coverage
+
! style="width: 9%" | Coverage
! style="width: 13%" | Testvoc
+
! style="width: 5%" | Testvoc
! style="width: 13%" | Bidix<br>(excluding<br>proper names)
+
! style="width: 5%" | Bidix<br>(excluding<br>proper names)
! style="width: 13%" | WER
+
! style="width: 8%" | WER
! style="width: 13%" | Coverage
+
! style="width: 9%" | Coverage
! style="width: 13%" | Testvoc
+
! style="width: 9%" | Testvoc<br>(clean %)
! style="width: 8%" | Yes/No
+
! style="width: 5%" | Yes/No
 
|-
 
|-
 
! Initial situation
 
! Initial situation
Line 27: Line 27:
 
! Post-application period
 
! Post-application period
 
| style="text-align:center" | 10 March - 26 May
 
| style="text-align:center" | 10 March - 26 May
 
| colspan=4 |
| style="text-align:center" |
 
| style="text-align:center" |
 
| style="text-align:center" |
 
| style="text-align:center" |
 
 
| colspan=5 |
 
| colspan=5 |
 
* simplified the cat-ita bidix dropping 500+lines using paradigms, so the initial situation came to ~8,500 words
 
* simplified the cat-ita bidix dropping 500+lines using paradigms, so the initial situation came to ~8,500 words
Line 43: Line 40:
 
| style="text-align:center" | ~85.5% (ita > cat)
 
| style="text-align:center" | ~85.5% (ita > cat)
 
| style="text-align:center" |
 
| style="text-align:center" |
  +
| style="text-align:center" | 11,502
! colspan=5 |
 
 
| style="text-align:center" |
  +
| style="text-align:center" | 86.1%
 
| style="text-align:center" |
  +
| style="text-align:center" | ✓
 
|-
 
|-
 
! 2
 
! 2
Line 51: Line 52:
 
| style="text-align:center" | ~87.5% (ita > cat)
 
| style="text-align:center" | ~87.5% (ita > cat)
 
| style="text-align:center" |
 
| style="text-align:center" |
  +
| style="text-align:center" | 13,102
! colspan=5 |
 
 
| style="text-align:center" |
  +
| style="text-align:center" | 87.1%
 
| style="text-align:center" |
  +
| style="text-align:center" |
 
|-
 
|-
 
! 3
 
! 3
Line 58: Line 63:
 
| style="text-align:center" | <20% (ita > cat)
 
| style="text-align:center" | <20% (ita > cat)
 
| style="text-align:center" | ~89% (ita > cat)
 
| style="text-align:center" | ~89% (ita > cat)
  +
| style="text-align:center" |
|
 
  +
| style="text-align:center" | 18,704
! colspan=5 |
 
  +
| style="text-align:center" | 28.7%
  +
| style="text-align:center" | 89.4%
  +
| style="text-align:center" |
  +
| style="text-align:center" |
 
|-
 
|-
 
! colspan=11 | '''cat > ita'''
 
! colspan=11 | '''cat > ita'''
Line 69: Line 78:
 
| style="text-align:center" | ~90% (cat > ita)<br>~90% (ita > cat)
 
| style="text-align:center" | ~90% (cat > ita)<br>~90% (ita > cat)
 
| style="text-align:center" | closed categories
 
| style="text-align:center" | closed categories
  +
| style="text-align:center" | 20,113
! colspan=5 |
 
  +
| style="text-align:center" | 20.6% (ita > cat)
  +
| style="text-align:center" | 93.9% (cat > ita)<br>90.6% (ita > cat)
  +
| style="text-align:center" | 100%
  +
| style="text-align:center" |
 
|-
 
|-
 
! 5
 
! 5
Line 77: Line 90:
 
| style="text-align:center" | ~90.5% (cat > ita)<br>~90.5% (ita > cat)
 
| style="text-align:center" | ~90.5% (cat > ita)<br>~90.5% (ita > cat)
 
| style="text-align:center" | vblex
 
| style="text-align:center" | vblex
  +
| style="text-align:center" | 21,017
! colspan=5 |
 
  +
| style="text-align:center" |
  +
| style="text-align:center" | 94.2% (cat > ita)<br>91.0% (ita > cat)
  +
| style="text-align:center" | 74.0% (cat > ita)<br>100% (ita > cat)
  +
| style="text-align:center" |
 
|-
 
|-
 
! 6
 
! 6
Line 85: Line 102:
 
| style="text-align:center" | ~91% (cat > ita)<br>~91% (ita > cat)
 
| style="text-align:center" | ~91% (cat > ita)<br>~91% (ita > cat)
 
| style="text-align:center" | adj, adv, np
 
| style="text-align:center" | adj, adv, np
  +
| style="text-align:center" | 21,217
! colspan=5 |
 
  +
| style="text-align:center" |
  +
| style="text-align:center" | 94.3% (cat > ita)<br>91.1% (ita > cat)
  +
| style="text-align:center" | vblex<br>99.9% (cat > ita)<br>adj, adv, np<br>100%
  +
| style="text-align:center" |
 
|-
 
|-
 
! 7
 
! 7
Line 93: Line 114:
 
| style="text-align:center" | ~91.5% (cat > ita)<br>~91.5% (ita > cat)
 
| style="text-align:center" | ~91.5% (cat > ita)<br>~91.5% (ita > cat)
 
| style="text-align:center" | n
 
| style="text-align:center" | n
  +
| style="text-align:center" | 21,907
! colspan=5 |
 
  +
| style="text-align:center" | 14.2% (cat > ita)<br>15.7% (ita > cat)
  +
| style="text-align:center" | 94.7% (cat > ita)<br>91.2% (ita > cat)
  +
| style="text-align:center" | 0
  +
| style="text-align:center" |
 
|-
 
|-
 
! colspan=11 | '''por > cat'''
 
! colspan=11 | '''por > cat'''
Line 103: Line 128:
 
| style="text-align:center" | ~87% (por > cat)
 
| style="text-align:center" | ~87% (por > cat)
 
| style="text-align:center" |
 
| style="text-align:center" |
  +
| style="text-align:center" | 9,239
! colspan=5 |
 
  +
| style="text-align:center" |
  +
| style="text-align:center" | 87.3%
  +
| style="text-align:center" |
  +
| style="text-align:center" |
 
|-
 
|-
 
! 9
 
! 9
Line 110: Line 139:
 
| style="text-align:center" |
 
| style="text-align:center" |
 
| style="text-align:center" | ~89% (por > cat)
 
| style="text-align:center" | ~89% (por > cat)
| style="text-align:center" | np
+
| style="text-align:center" |
  +
| style="text-align:center" | 11,858
! colspan=5 |
 
  +
| style="text-align:center" |
  +
| style="text-align:center" | 88.5%
  +
| style="text-align:center" |
  +
| style="text-align:center" |
 
|-
 
|-
 
! 10
 
! 10
Line 118: Line 151:
 
| style="text-align:center" | <20% (por > cat)
 
| style="text-align:center" | <20% (por > cat)
 
| style="text-align:center" | ~89.5% (por > cat)
 
| style="text-align:center" | ~89.5% (por > cat)
  +
| style="text-align:center" | np
  +
| style="text-align:center" | 23,235
  +
| style="text-align:center" | 11.9%
  +
| style="text-align:center" | 90.2%
  +
| style="text-align:center" | 67
 
| style="text-align:center" |
 
| style="text-align:center" |
! colspan=5 |
 
 
|-
 
|-
! colspan=11 |
+
! colspan=11 | '''cat > por'''
 
|-
 
|-
 
! 11
 
! 11
Line 129: Line 166:
 
| style="text-align:center" | ~90% (cat > por)<br>~90% (por > cat)
 
| style="text-align:center" | ~90% (cat > por)<br>~90% (por > cat)
 
| style="text-align:center" | closed categories, vblex
 
| style="text-align:center" | closed categories, vblex
  +
| style="text-align:center" | 24,037
! colspan=5 |
 
  +
| style="text-align:center" |
  +
| style="text-align:center" | 93.5% (cat > por)<br>90.8% (por > cat)
  +
| style="text-align:center" | np: 10+1<br>vblex: 0+1853<br>closed cat.: 23+179
  +
| style="text-align:center" |
 
|-
 
|-
 
! 12
 
! 12
Line 137: Line 178:
 
| style="text-align:center" | ~90.5% (cat > por)<br>~90.5% (por > cat)
 
| style="text-align:center" | ~90.5% (cat > por)<br>~90.5% (por > cat)
 
| style="text-align:center" | adj, adv
 
| style="text-align:center" | adj, adv
  +
| style="text-align:center" | 25,557
! colspan=5 |
 
  +
| style="text-align:center" |
  +
| style="text-align:center" | 94.1% (cat > por)<br>91.2% (por > cat)
  +
| style="text-align:center" | 0
  +
| style="text-align:center" |
 
|-
 
|-
 
! 13
 
! 13
Line 145: Line 190:
 
| style="text-align:center" | ~91.0% (cat > por)<br>~91.0% (por > cat)
 
| style="text-align:center" | ~91.0% (cat > por)<br>~91.0% (por > cat)
 
| style="text-align:center" | n
 
| style="text-align:center" | n
  +
| style="text-align:center" | 25,823
! colspan=5 |
 
  +
| style="text-align:center" | (cat > por)<br>14.0% (por > cat)
  +
| style="text-align:center" | 94.4% (cat > por)<br>91.4% (por > cat)
  +
| style="text-align:center" | 0
  +
| style="text-align:center" |
 
|}
 
|}
  +
  +
=== See also ===
  +
[[Hectoralos/GSOC_2019_proposal:_Catalan-Italian_and_Catalan-Portuguese#Workplan | Work plan in the original proposal]]

Latest revision as of 21:35, 24 August 2019

Workplan[edit]

Week Dates Goals Fulfilled
Bidix
(excluding
proper names)
WER Coverage Testvoc Bidix
(excluding
proper names)
WER Coverage Testvoc
(clean %)
Yes/No
Initial situation ~9,000 (cat-ita)
~7,500 (cat-por)
~30% (cat > ita)
~30% (cat > por)
~30% (por > cat)
~88% (cat > ita)
~82% (ita > cat)
~88% (cat > por)
~84% (por > cat)
Post-application period 10 March - 26 May
  • simplified the cat-ita bidix dropping 500+lines using paradigms, so the initial situation came to ~8,500 words
  • began some work with bidix, i.a. loaded np.cog
ita > cat
1 27 May - 2 June ~11,000 (cat-ita) ~85.5% (ita > cat) 11,502 86.1%
2 3 June- 9 June ~13,000 (cat-ita) ~87.5% (ita > cat) 13,102 87.1%
3 10 June - 16 June ~14,000 (cat-ita) <20% (ita > cat) ~89% (ita > cat) 18,704 28.7% 89.4%
cat > ita
4 17 June - 23 June ~15,000 (cat-ita) ~90% (cat > ita)
~90% (ita > cat)
closed categories 20,113 20.6% (ita > cat) 93.9% (cat > ita)
90.6% (ita > cat)
100%
5 24 June - 30 June ~16,000 (cat-ita) ~90.5% (cat > ita)
~90.5% (ita > cat)
vblex 21,017 94.2% (cat > ita)
91.0% (ita > cat)
74.0% (cat > ita)
100% (ita > cat)
6 1 July - 7 July ~17,000 (cat-ita) ~91% (cat > ita)
~91% (ita > cat)
adj, adv, np 21,217 94.3% (cat > ita)
91.1% (ita > cat)
vblex
99.9% (cat > ita)
adj, adv, np
100%
7 8 June - 14 July ~18,000 (cat-ita) <15% (cat > ita)
<15% (ita > cat)
~91.5% (cat > ita)
~91.5% (ita > cat)
n 21,907 14.2% (cat > ita)
15.7% (ita > cat)
94.7% (cat > ita)
91.2% (ita > cat)
0
por > cat
8 15 July - 21 July ~9,500 (cat-por) ~87% (por > cat) 9,239 87.3%
9 22 July - 28 July ~11,500 (cat-por) ~89% (por > cat) 11,858 88.5%
10 29 July - 4 August ~13,000 (cat-por) <20% (por > cat) ~89.5% (por > cat) np 23,235 11.9% 90.2% 67
cat > por
11 5 August - 11 August ~14,500 (cat-por) ~90% (cat > por)
~90% (por > cat)
closed categories, vblex 24,037 93.5% (cat > por)
90.8% (por > cat)
np: 10+1
vblex: 0+1853
closed cat.: 23+179
12 12 August - 18 August ~16,000 (cat-por) ~90.5% (cat > por)
~90.5% (por > cat)
adj, adv 25,557 94.1% (cat > por)
91.2% (por > cat)
0
13 18 August - 25 August ~17,000 (cat-por) <15% (cat > por)
<15% (por > cat)
~91.0% (cat > por)
~91.0% (por > cat)
n 25,823 (cat > por)
14.0% (por > cat)
94.4% (cat > por)
91.4% (por > cat)
0

See also[edit]

Work plan in the original proposal