Spaces:
Running
Running
David Pomerenke
commited on
Commit
·
b909c3a
1
Parent(s):
0e5691e
Add chart with #speakers vs BLEU
Browse files- index.html +27 -1
- languagebench.py +3 -3
- results.json +40 -40
- results_summary.json +16 -8
index.html
CHANGED
|
@@ -33,7 +33,33 @@
|
|
| 33 |
import * as Plot from "https://cdn.jsdelivr.net/npm/@observablehq/[email protected]/+esm";
|
| 34 |
|
| 35 |
async function init() {
|
|
|
|
|
|
|
| 36 |
const summary = await fetch('results_summary.json');
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
const response = await fetch('results.json');
|
| 39 |
const results = await response.json();
|
|
@@ -51,7 +77,7 @@
|
|
| 51 |
.sort((a, b) => b[1] - a[1])
|
| 52 |
.map(([lang]) => lang);
|
| 53 |
|
| 54 |
-
|
| 55 |
|
| 56 |
languages.forEach(language => {
|
| 57 |
const headerDiv = document.createElement('div');
|
|
|
|
| 33 |
import * as Plot from "https://cdn.jsdelivr.net/npm/@observablehq/[email protected]/+esm";
|
| 34 |
|
| 35 |
async function init() {
|
| 36 |
+
const chartsDiv = document.getElementById('charts');
|
| 37 |
+
|
| 38 |
const summary = await fetch('results_summary.json');
|
| 39 |
+
const summaryData = await summary.json();
|
| 40 |
+
|
| 41 |
+
// Create summary plot
|
| 42 |
+
const summaryPlot = Plot.plot({
|
| 43 |
+
width: 800,
|
| 44 |
+
height: 400,
|
| 45 |
+
x: { label: "Number of speakers" },
|
| 46 |
+
y: { label: "BLEU Score (average across models)" },
|
| 47 |
+
marks: [
|
| 48 |
+
Plot.rectY(summaryData, Plot.stackX({
|
| 49 |
+
x: "speakers",
|
| 50 |
+
order: "bleu",
|
| 51 |
+
reverse: true,
|
| 52 |
+
y2: "bleu", // y2 to avoid stacking by y
|
| 53 |
+
title: (d) => `${d.target_language_name}\n${d.bleu.toFixed(1)}`,
|
| 54 |
+
insetLeft: 0.2,
|
| 55 |
+
insetRight: 0.2
|
| 56 |
+
})),
|
| 57 |
+
Plot.ruleY([0])
|
| 58 |
+
]
|
| 59 |
+
});
|
| 60 |
+
|
| 61 |
+
// Add summary plot at the top
|
| 62 |
+
chartsDiv.insertBefore(summaryPlot, chartsDiv.firstChild);
|
| 63 |
|
| 64 |
const response = await fetch('results.json');
|
| 65 |
const results = await response.json();
|
|
|
|
| 77 |
.sort((a, b) => b[1] - a[1])
|
| 78 |
.map(([lang]) => lang);
|
| 79 |
|
| 80 |
+
|
| 81 |
|
| 82 |
languages.forEach(language => {
|
| 83 |
const headerDiv = document.createElement('div');
|
languagebench.py
CHANGED
|
@@ -25,7 +25,7 @@ original_language = "eng_Latn"
|
|
| 25 |
dataset = "floresp-v2.0-rc.3/dev"
|
| 26 |
random.seed(42)
|
| 27 |
target_languages = [f.split(".")[1] for f in os.listdir(dataset)]
|
| 28 |
-
target_languages = random.choices(target_languages, k=
|
| 29 |
# target_languages = [
|
| 30 |
# "eng_Latn",
|
| 31 |
# "deu_Latn",
|
|
@@ -124,7 +124,7 @@ async def main():
|
|
| 124 |
"original_language": original_language,
|
| 125 |
"target_language": target_language,
|
| 126 |
"target_language_name": stats["name"],
|
| 127 |
-
"speakers": stats.get("maxSpeakers"),
|
| 128 |
"bleu": metrics["score"],
|
| 129 |
}
|
| 130 |
)
|
|
@@ -132,7 +132,7 @@ async def main():
|
|
| 132 |
json.dump(results, f, indent=2, ensure_ascii=False)
|
| 133 |
# compute mean bleu for each target language
|
| 134 |
pd.DataFrame(results).groupby("target_language_name").agg(
|
| 135 |
-
{"bleu": "mean"}
|
| 136 |
).reset_index().to_json("results_summary.json", indent=2, orient="records")
|
| 137 |
|
| 138 |
|
|
|
|
| 25 |
dataset = "floresp-v2.0-rc.3/dev"
|
| 26 |
random.seed(42)
|
| 27 |
target_languages = [f.split(".")[1] for f in os.listdir(dataset)]
|
| 28 |
+
target_languages = random.choices(target_languages, k=8)
|
| 29 |
# target_languages = [
|
| 30 |
# "eng_Latn",
|
| 31 |
# "deu_Latn",
|
|
|
|
| 124 |
"original_language": original_language,
|
| 125 |
"target_language": target_language,
|
| 126 |
"target_language_name": stats["name"],
|
| 127 |
+
"speakers": int(stats.get("maxSpeakers", 0)),
|
| 128 |
"bleu": metrics["score"],
|
| 129 |
}
|
| 130 |
)
|
|
|
|
| 132 |
json.dump(results, f, indent=2, ensure_ascii=False)
|
| 133 |
# compute mean bleu for each target language
|
| 134 |
pd.DataFrame(results).groupby("target_language_name").agg(
|
| 135 |
+
{"bleu": "mean", "speakers": "mean"}
|
| 136 |
).reset_index().to_json("results_summary.json", indent=2, orient="records")
|
| 137 |
|
| 138 |
|
results.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"original_language": "eng_Latn",
|
| 5 |
"target_language": "isl_Latn",
|
| 6 |
"target_language_name": "Icelandic",
|
| 7 |
-
"speakers":
|
| 8 |
"bleu": 61.64765463591684
|
| 9 |
},
|
| 10 |
{
|
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"original_language": "eng_Latn",
|
| 13 |
"target_language": "isl_Latn",
|
| 14 |
"target_language_name": "Icelandic",
|
| 15 |
-
"speakers":
|
| 16 |
"bleu": 58.800114937175536
|
| 17 |
},
|
| 18 |
{
|
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"original_language": "eng_Latn",
|
| 21 |
"target_language": "isl_Latn",
|
| 22 |
"target_language_name": "Icelandic",
|
| 23 |
-
"speakers":
|
| 24 |
"bleu": 63.29310272337262
|
| 25 |
},
|
| 26 |
{
|
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"original_language": "eng_Latn",
|
| 29 |
"target_language": "isl_Latn",
|
| 30 |
"target_language_name": "Icelandic",
|
| 31 |
-
"speakers":
|
| 32 |
"bleu": 28.81229691079592
|
| 33 |
},
|
| 34 |
{
|
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"original_language": "eng_Latn",
|
| 37 |
"target_language": "isl_Latn",
|
| 38 |
"target_language_name": "Icelandic",
|
| 39 |
-
"speakers":
|
| 40 |
"bleu": 35.26511601216665
|
| 41 |
},
|
| 42 |
{
|
|
@@ -44,7 +44,7 @@
|
|
| 44 |
"original_language": "eng_Latn",
|
| 45 |
"target_language": "ind_Latn",
|
| 46 |
"target_language_name": "Indonesian",
|
| 47 |
-
"speakers":
|
| 48 |
"bleu": 77.046561794683
|
| 49 |
},
|
| 50 |
{
|
|
@@ -52,7 +52,7 @@
|
|
| 52 |
"original_language": "eng_Latn",
|
| 53 |
"target_language": "ind_Latn",
|
| 54 |
"target_language_name": "Indonesian",
|
| 55 |
-
"speakers":
|
| 56 |
"bleu": 73.29149877209336
|
| 57 |
},
|
| 58 |
{
|
|
@@ -60,7 +60,7 @@
|
|
| 60 |
"original_language": "eng_Latn",
|
| 61 |
"target_language": "ind_Latn",
|
| 62 |
"target_language_name": "Indonesian",
|
| 63 |
-
"speakers":
|
| 64 |
"bleu": 71.2935146236652
|
| 65 |
},
|
| 66 |
{
|
|
@@ -68,7 +68,7 @@
|
|
| 68 |
"original_language": "eng_Latn",
|
| 69 |
"target_language": "ind_Latn",
|
| 70 |
"target_language_name": "Indonesian",
|
| 71 |
-
"speakers":
|
| 72 |
"bleu": 71.24329964015463
|
| 73 |
},
|
| 74 |
{
|
|
@@ -76,7 +76,7 @@
|
|
| 76 |
"original_language": "eng_Latn",
|
| 77 |
"target_language": "ind_Latn",
|
| 78 |
"target_language_name": "Indonesian",
|
| 79 |
-
"speakers":
|
| 80 |
"bleu": 68.73551514908719
|
| 81 |
},
|
| 82 |
{
|
|
@@ -84,7 +84,7 @@
|
|
| 84 |
"original_language": "eng_Latn",
|
| 85 |
"target_language": "pol_Latn",
|
| 86 |
"target_language_name": "Polish",
|
| 87 |
-
"speakers":
|
| 88 |
"bleu": 65.22066652766671
|
| 89 |
},
|
| 90 |
{
|
|
@@ -92,7 +92,7 @@
|
|
| 92 |
"original_language": "eng_Latn",
|
| 93 |
"target_language": "pol_Latn",
|
| 94 |
"target_language_name": "Polish",
|
| 95 |
-
"speakers":
|
| 96 |
"bleu": 64.9142026045634
|
| 97 |
},
|
| 98 |
{
|
|
@@ -100,7 +100,7 @@
|
|
| 100 |
"original_language": "eng_Latn",
|
| 101 |
"target_language": "pol_Latn",
|
| 102 |
"target_language_name": "Polish",
|
| 103 |
-
"speakers":
|
| 104 |
"bleu": 62.0169794404058
|
| 105 |
},
|
| 106 |
{
|
|
@@ -108,7 +108,7 @@
|
|
| 108 |
"original_language": "eng_Latn",
|
| 109 |
"target_language": "pol_Latn",
|
| 110 |
"target_language_name": "Polish",
|
| 111 |
-
"speakers":
|
| 112 |
"bleu": 50.22137732799528
|
| 113 |
},
|
| 114 |
{
|
|
@@ -116,7 +116,7 @@
|
|
| 116 |
"original_language": "eng_Latn",
|
| 117 |
"target_language": "pol_Latn",
|
| 118 |
"target_language_name": "Polish",
|
| 119 |
-
"speakers":
|
| 120 |
"bleu": 54.39716369344653
|
| 121 |
},
|
| 122 |
{
|
|
@@ -124,7 +124,7 @@
|
|
| 124 |
"original_language": "eng_Latn",
|
| 125 |
"target_language": "kas_Deva",
|
| 126 |
"target_language_name": "Kashmiri",
|
| 127 |
-
"speakers":
|
| 128 |
"bleu": 22.853844625462184
|
| 129 |
},
|
| 130 |
{
|
|
@@ -132,7 +132,7 @@
|
|
| 132 |
"original_language": "eng_Latn",
|
| 133 |
"target_language": "kas_Deva",
|
| 134 |
"target_language_name": "Kashmiri",
|
| 135 |
-
"speakers":
|
| 136 |
"bleu": 1.6028583744267129
|
| 137 |
},
|
| 138 |
{
|
|
@@ -140,7 +140,7 @@
|
|
| 140 |
"original_language": "eng_Latn",
|
| 141 |
"target_language": "kas_Deva",
|
| 142 |
"target_language_name": "Kashmiri",
|
| 143 |
-
"speakers":
|
| 144 |
"bleu": 10.24928534626491
|
| 145 |
},
|
| 146 |
{
|
|
@@ -148,7 +148,7 @@
|
|
| 148 |
"original_language": "eng_Latn",
|
| 149 |
"target_language": "kas_Deva",
|
| 150 |
"target_language_name": "Kashmiri",
|
| 151 |
-
"speakers":
|
| 152 |
"bleu": 18.289957619904254
|
| 153 |
},
|
| 154 |
{
|
|
@@ -156,7 +156,7 @@
|
|
| 156 |
"original_language": "eng_Latn",
|
| 157 |
"target_language": "kas_Deva",
|
| 158 |
"target_language_name": "Kashmiri",
|
| 159 |
-
"speakers":
|
| 160 |
"bleu": 0.8669151440746464
|
| 161 |
},
|
| 162 |
{
|
|
@@ -164,7 +164,7 @@
|
|
| 164 |
"original_language": "eng_Latn",
|
| 165 |
"target_language": "lin_Latn",
|
| 166 |
"target_language_name": "Lingala",
|
| 167 |
-
"speakers":
|
| 168 |
"bleu": 50.873508850595044
|
| 169 |
},
|
| 170 |
{
|
|
@@ -172,7 +172,7 @@
|
|
| 172 |
"original_language": "eng_Latn",
|
| 173 |
"target_language": "lin_Latn",
|
| 174 |
"target_language_name": "Lingala",
|
| 175 |
-
"speakers":
|
| 176 |
"bleu": 6.943431977023627
|
| 177 |
},
|
| 178 |
{
|
|
@@ -180,7 +180,7 @@
|
|
| 180 |
"original_language": "eng_Latn",
|
| 181 |
"target_language": "lin_Latn",
|
| 182 |
"target_language_name": "Lingala",
|
| 183 |
-
"speakers":
|
| 184 |
"bleu": 45.048992005653
|
| 185 |
},
|
| 186 |
{
|
|
@@ -188,7 +188,7 @@
|
|
| 188 |
"original_language": "eng_Latn",
|
| 189 |
"target_language": "lin_Latn",
|
| 190 |
"target_language_name": "Lingala",
|
| 191 |
-
"speakers":
|
| 192 |
"bleu": 2.9809864732757902
|
| 193 |
},
|
| 194 |
{
|
|
@@ -196,7 +196,7 @@
|
|
| 196 |
"original_language": "eng_Latn",
|
| 197 |
"target_language": "lin_Latn",
|
| 198 |
"target_language_name": "Lingala",
|
| 199 |
-
"speakers":
|
| 200 |
"bleu": 0.5682271000080301
|
| 201 |
},
|
| 202 |
{
|
|
@@ -204,7 +204,7 @@
|
|
| 204 |
"original_language": "eng_Latn",
|
| 205 |
"target_language": "bjn_Latn",
|
| 206 |
"target_language_name": "Banjar",
|
| 207 |
-
"speakers":
|
| 208 |
"bleu": 50.02000892713302
|
| 209 |
},
|
| 210 |
{
|
|
@@ -212,7 +212,7 @@
|
|
| 212 |
"original_language": "eng_Latn",
|
| 213 |
"target_language": "bjn_Latn",
|
| 214 |
"target_language_name": "Banjar",
|
| 215 |
-
"speakers":
|
| 216 |
"bleu": 5.960932185623333
|
| 217 |
},
|
| 218 |
{
|
|
@@ -220,7 +220,7 @@
|
|
| 220 |
"original_language": "eng_Latn",
|
| 221 |
"target_language": "bjn_Latn",
|
| 222 |
"target_language_name": "Banjar",
|
| 223 |
-
"speakers":
|
| 224 |
"bleu": 46.23236901760108
|
| 225 |
},
|
| 226 |
{
|
|
@@ -228,7 +228,7 @@
|
|
| 228 |
"original_language": "eng_Latn",
|
| 229 |
"target_language": "bjn_Latn",
|
| 230 |
"target_language_name": "Banjar",
|
| 231 |
-
"speakers":
|
| 232 |
"bleu": 21.478973248564643
|
| 233 |
},
|
| 234 |
{
|
|
@@ -236,7 +236,7 @@
|
|
| 236 |
"original_language": "eng_Latn",
|
| 237 |
"target_language": "bjn_Latn",
|
| 238 |
"target_language_name": "Banjar",
|
| 239 |
-
"speakers":
|
| 240 |
"bleu": 22.371002216375594
|
| 241 |
},
|
| 242 |
{
|
|
@@ -244,7 +244,7 @@
|
|
| 244 |
"original_language": "eng_Latn",
|
| 245 |
"target_language": "bho_Deva",
|
| 246 |
"target_language_name": "Bhojpuri",
|
| 247 |
-
"speakers":
|
| 248 |
"bleu": 43.46871320382143
|
| 249 |
},
|
| 250 |
{
|
|
@@ -252,7 +252,7 @@
|
|
| 252 |
"original_language": "eng_Latn",
|
| 253 |
"target_language": "bho_Deva",
|
| 254 |
"target_language_name": "Bhojpuri",
|
| 255 |
-
"speakers":
|
| 256 |
"bleu": 18.253876118905147
|
| 257 |
},
|
| 258 |
{
|
|
@@ -260,7 +260,7 @@
|
|
| 260 |
"original_language": "eng_Latn",
|
| 261 |
"target_language": "bho_Deva",
|
| 262 |
"target_language_name": "Bhojpuri",
|
| 263 |
-
"speakers":
|
| 264 |
"bleu": 23.447356116551486
|
| 265 |
},
|
| 266 |
{
|
|
@@ -268,7 +268,7 @@
|
|
| 268 |
"original_language": "eng_Latn",
|
| 269 |
"target_language": "bho_Deva",
|
| 270 |
"target_language_name": "Bhojpuri",
|
| 271 |
-
"speakers":
|
| 272 |
"bleu": 29.81946758376717
|
| 273 |
},
|
| 274 |
{
|
|
@@ -276,7 +276,7 @@
|
|
| 276 |
"original_language": "eng_Latn",
|
| 277 |
"target_language": "bho_Deva",
|
| 278 |
"target_language_name": "Bhojpuri",
|
| 279 |
-
"speakers":
|
| 280 |
"bleu": 3.2486895985868474
|
| 281 |
},
|
| 282 |
{
|
|
@@ -284,7 +284,7 @@
|
|
| 284 |
"original_language": "eng_Latn",
|
| 285 |
"target_language": "ces_Latn",
|
| 286 |
"target_language_name": "Czech",
|
| 287 |
-
"speakers":
|
| 288 |
"bleu": 69.01583822081993
|
| 289 |
},
|
| 290 |
{
|
|
@@ -292,7 +292,7 @@
|
|
| 292 |
"original_language": "eng_Latn",
|
| 293 |
"target_language": "ces_Latn",
|
| 294 |
"target_language_name": "Czech",
|
| 295 |
-
"speakers":
|
| 296 |
"bleu": 69.4260447999661
|
| 297 |
},
|
| 298 |
{
|
|
@@ -300,7 +300,7 @@
|
|
| 300 |
"original_language": "eng_Latn",
|
| 301 |
"target_language": "ces_Latn",
|
| 302 |
"target_language_name": "Czech",
|
| 303 |
-
"speakers":
|
| 304 |
"bleu": 68.6109083634317
|
| 305 |
},
|
| 306 |
{
|
|
@@ -308,7 +308,7 @@
|
|
| 308 |
"original_language": "eng_Latn",
|
| 309 |
"target_language": "ces_Latn",
|
| 310 |
"target_language_name": "Czech",
|
| 311 |
-
"speakers":
|
| 312 |
"bleu": 59.72501366200287
|
| 313 |
},
|
| 314 |
{
|
|
@@ -316,7 +316,7 @@
|
|
| 316 |
"original_language": "eng_Latn",
|
| 317 |
"target_language": "ces_Latn",
|
| 318 |
"target_language_name": "Czech",
|
| 319 |
-
"speakers":
|
| 320 |
"bleu": 60.25088578142904
|
| 321 |
}
|
| 322 |
]
|
|
|
|
| 4 |
"original_language": "eng_Latn",
|
| 5 |
"target_language": "isl_Latn",
|
| 6 |
"target_language_name": "Icelandic",
|
| 7 |
+
"speakers": 358000,
|
| 8 |
"bleu": 61.64765463591684
|
| 9 |
},
|
| 10 |
{
|
|
|
|
| 12 |
"original_language": "eng_Latn",
|
| 13 |
"target_language": "isl_Latn",
|
| 14 |
"target_language_name": "Icelandic",
|
| 15 |
+
"speakers": 358000,
|
| 16 |
"bleu": 58.800114937175536
|
| 17 |
},
|
| 18 |
{
|
|
|
|
| 20 |
"original_language": "eng_Latn",
|
| 21 |
"target_language": "isl_Latn",
|
| 22 |
"target_language_name": "Icelandic",
|
| 23 |
+
"speakers": 358000,
|
| 24 |
"bleu": 63.29310272337262
|
| 25 |
},
|
| 26 |
{
|
|
|
|
| 28 |
"original_language": "eng_Latn",
|
| 29 |
"target_language": "isl_Latn",
|
| 30 |
"target_language_name": "Icelandic",
|
| 31 |
+
"speakers": 358000,
|
| 32 |
"bleu": 28.81229691079592
|
| 33 |
},
|
| 34 |
{
|
|
|
|
| 36 |
"original_language": "eng_Latn",
|
| 37 |
"target_language": "isl_Latn",
|
| 38 |
"target_language_name": "Icelandic",
|
| 39 |
+
"speakers": 358000,
|
| 40 |
"bleu": 35.26511601216665
|
| 41 |
},
|
| 42 |
{
|
|
|
|
| 44 |
"original_language": "eng_Latn",
|
| 45 |
"target_language": "ind_Latn",
|
| 46 |
"target_language_name": "Indonesian",
|
| 47 |
+
"speakers": 198996550,
|
| 48 |
"bleu": 77.046561794683
|
| 49 |
},
|
| 50 |
{
|
|
|
|
| 52 |
"original_language": "eng_Latn",
|
| 53 |
"target_language": "ind_Latn",
|
| 54 |
"target_language_name": "Indonesian",
|
| 55 |
+
"speakers": 198996550,
|
| 56 |
"bleu": 73.29149877209336
|
| 57 |
},
|
| 58 |
{
|
|
|
|
| 60 |
"original_language": "eng_Latn",
|
| 61 |
"target_language": "ind_Latn",
|
| 62 |
"target_language_name": "Indonesian",
|
| 63 |
+
"speakers": 198996550,
|
| 64 |
"bleu": 71.2935146236652
|
| 65 |
},
|
| 66 |
{
|
|
|
|
| 68 |
"original_language": "eng_Latn",
|
| 69 |
"target_language": "ind_Latn",
|
| 70 |
"target_language_name": "Indonesian",
|
| 71 |
+
"speakers": 198996550,
|
| 72 |
"bleu": 71.24329964015463
|
| 73 |
},
|
| 74 |
{
|
|
|
|
| 76 |
"original_language": "eng_Latn",
|
| 77 |
"target_language": "ind_Latn",
|
| 78 |
"target_language_name": "Indonesian",
|
| 79 |
+
"speakers": 198996550,
|
| 80 |
"bleu": 68.73551514908719
|
| 81 |
},
|
| 82 |
{
|
|
|
|
| 84 |
"original_language": "eng_Latn",
|
| 85 |
"target_language": "pol_Latn",
|
| 86 |
"target_language_name": "Polish",
|
| 87 |
+
"speakers": 40200000,
|
| 88 |
"bleu": 65.22066652766671
|
| 89 |
},
|
| 90 |
{
|
|
|
|
| 92 |
"original_language": "eng_Latn",
|
| 93 |
"target_language": "pol_Latn",
|
| 94 |
"target_language_name": "Polish",
|
| 95 |
+
"speakers": 40200000,
|
| 96 |
"bleu": 64.9142026045634
|
| 97 |
},
|
| 98 |
{
|
|
|
|
| 100 |
"original_language": "eng_Latn",
|
| 101 |
"target_language": "pol_Latn",
|
| 102 |
"target_language_name": "Polish",
|
| 103 |
+
"speakers": 40200000,
|
| 104 |
"bleu": 62.0169794404058
|
| 105 |
},
|
| 106 |
{
|
|
|
|
| 108 |
"original_language": "eng_Latn",
|
| 109 |
"target_language": "pol_Latn",
|
| 110 |
"target_language_name": "Polish",
|
| 111 |
+
"speakers": 40200000,
|
| 112 |
"bleu": 50.22137732799528
|
| 113 |
},
|
| 114 |
{
|
|
|
|
| 116 |
"original_language": "eng_Latn",
|
| 117 |
"target_language": "pol_Latn",
|
| 118 |
"target_language_name": "Polish",
|
| 119 |
+
"speakers": 40200000,
|
| 120 |
"bleu": 54.39716369344653
|
| 121 |
},
|
| 122 |
{
|
|
|
|
| 124 |
"original_language": "eng_Latn",
|
| 125 |
"target_language": "kas_Deva",
|
| 126 |
"target_language_name": "Kashmiri",
|
| 127 |
+
"speakers": 6900000,
|
| 128 |
"bleu": 22.853844625462184
|
| 129 |
},
|
| 130 |
{
|
|
|
|
| 132 |
"original_language": "eng_Latn",
|
| 133 |
"target_language": "kas_Deva",
|
| 134 |
"target_language_name": "Kashmiri",
|
| 135 |
+
"speakers": 6900000,
|
| 136 |
"bleu": 1.6028583744267129
|
| 137 |
},
|
| 138 |
{
|
|
|
|
| 140 |
"original_language": "eng_Latn",
|
| 141 |
"target_language": "kas_Deva",
|
| 142 |
"target_language_name": "Kashmiri",
|
| 143 |
+
"speakers": 6900000,
|
| 144 |
"bleu": 10.24928534626491
|
| 145 |
},
|
| 146 |
{
|
|
|
|
| 148 |
"original_language": "eng_Latn",
|
| 149 |
"target_language": "kas_Deva",
|
| 150 |
"target_language_name": "Kashmiri",
|
| 151 |
+
"speakers": 6900000,
|
| 152 |
"bleu": 18.289957619904254
|
| 153 |
},
|
| 154 |
{
|
|
|
|
| 156 |
"original_language": "eng_Latn",
|
| 157 |
"target_language": "kas_Deva",
|
| 158 |
"target_language_name": "Kashmiri",
|
| 159 |
+
"speakers": 6900000,
|
| 160 |
"bleu": 0.8669151440746464
|
| 161 |
},
|
| 162 |
{
|
|
|
|
| 164 |
"original_language": "eng_Latn",
|
| 165 |
"target_language": "lin_Latn",
|
| 166 |
"target_language_name": "Lingala",
|
| 167 |
+
"speakers": 20000000,
|
| 168 |
"bleu": 50.873508850595044
|
| 169 |
},
|
| 170 |
{
|
|
|
|
| 172 |
"original_language": "eng_Latn",
|
| 173 |
"target_language": "lin_Latn",
|
| 174 |
"target_language_name": "Lingala",
|
| 175 |
+
"speakers": 20000000,
|
| 176 |
"bleu": 6.943431977023627
|
| 177 |
},
|
| 178 |
{
|
|
|
|
| 180 |
"original_language": "eng_Latn",
|
| 181 |
"target_language": "lin_Latn",
|
| 182 |
"target_language_name": "Lingala",
|
| 183 |
+
"speakers": 20000000,
|
| 184 |
"bleu": 45.048992005653
|
| 185 |
},
|
| 186 |
{
|
|
|
|
| 188 |
"original_language": "eng_Latn",
|
| 189 |
"target_language": "lin_Latn",
|
| 190 |
"target_language_name": "Lingala",
|
| 191 |
+
"speakers": 20000000,
|
| 192 |
"bleu": 2.9809864732757902
|
| 193 |
},
|
| 194 |
{
|
|
|
|
| 196 |
"original_language": "eng_Latn",
|
| 197 |
"target_language": "lin_Latn",
|
| 198 |
"target_language_name": "Lingala",
|
| 199 |
+
"speakers": 20000000,
|
| 200 |
"bleu": 0.5682271000080301
|
| 201 |
},
|
| 202 |
{
|
|
|
|
| 204 |
"original_language": "eng_Latn",
|
| 205 |
"target_language": "bjn_Latn",
|
| 206 |
"target_language_name": "Banjar",
|
| 207 |
+
"speakers": 3500000,
|
| 208 |
"bleu": 50.02000892713302
|
| 209 |
},
|
| 210 |
{
|
|
|
|
| 212 |
"original_language": "eng_Latn",
|
| 213 |
"target_language": "bjn_Latn",
|
| 214 |
"target_language_name": "Banjar",
|
| 215 |
+
"speakers": 3500000,
|
| 216 |
"bleu": 5.960932185623333
|
| 217 |
},
|
| 218 |
{
|
|
|
|
| 220 |
"original_language": "eng_Latn",
|
| 221 |
"target_language": "bjn_Latn",
|
| 222 |
"target_language_name": "Banjar",
|
| 223 |
+
"speakers": 3500000,
|
| 224 |
"bleu": 46.23236901760108
|
| 225 |
},
|
| 226 |
{
|
|
|
|
| 228 |
"original_language": "eng_Latn",
|
| 229 |
"target_language": "bjn_Latn",
|
| 230 |
"target_language_name": "Banjar",
|
| 231 |
+
"speakers": 3500000,
|
| 232 |
"bleu": 21.478973248564643
|
| 233 |
},
|
| 234 |
{
|
|
|
|
| 236 |
"original_language": "eng_Latn",
|
| 237 |
"target_language": "bjn_Latn",
|
| 238 |
"target_language_name": "Banjar",
|
| 239 |
+
"speakers": 3500000,
|
| 240 |
"bleu": 22.371002216375594
|
| 241 |
},
|
| 242 |
{
|
|
|
|
| 244 |
"original_language": "eng_Latn",
|
| 245 |
"target_language": "bho_Deva",
|
| 246 |
"target_language_name": "Bhojpuri",
|
| 247 |
+
"speakers": 52200000,
|
| 248 |
"bleu": 43.46871320382143
|
| 249 |
},
|
| 250 |
{
|
|
|
|
| 252 |
"original_language": "eng_Latn",
|
| 253 |
"target_language": "bho_Deva",
|
| 254 |
"target_language_name": "Bhojpuri",
|
| 255 |
+
"speakers": 52200000,
|
| 256 |
"bleu": 18.253876118905147
|
| 257 |
},
|
| 258 |
{
|
|
|
|
| 260 |
"original_language": "eng_Latn",
|
| 261 |
"target_language": "bho_Deva",
|
| 262 |
"target_language_name": "Bhojpuri",
|
| 263 |
+
"speakers": 52200000,
|
| 264 |
"bleu": 23.447356116551486
|
| 265 |
},
|
| 266 |
{
|
|
|
|
| 268 |
"original_language": "eng_Latn",
|
| 269 |
"target_language": "bho_Deva",
|
| 270 |
"target_language_name": "Bhojpuri",
|
| 271 |
+
"speakers": 52200000,
|
| 272 |
"bleu": 29.81946758376717
|
| 273 |
},
|
| 274 |
{
|
|
|
|
| 276 |
"original_language": "eng_Latn",
|
| 277 |
"target_language": "bho_Deva",
|
| 278 |
"target_language_name": "Bhojpuri",
|
| 279 |
+
"speakers": 52200000,
|
| 280 |
"bleu": 3.2486895985868474
|
| 281 |
},
|
| 282 |
{
|
|
|
|
| 284 |
"original_language": "eng_Latn",
|
| 285 |
"target_language": "ces_Latn",
|
| 286 |
"target_language_name": "Czech",
|
| 287 |
+
"speakers": 10700000,
|
| 288 |
"bleu": 69.01583822081993
|
| 289 |
},
|
| 290 |
{
|
|
|
|
| 292 |
"original_language": "eng_Latn",
|
| 293 |
"target_language": "ces_Latn",
|
| 294 |
"target_language_name": "Czech",
|
| 295 |
+
"speakers": 10700000,
|
| 296 |
"bleu": 69.4260447999661
|
| 297 |
},
|
| 298 |
{
|
|
|
|
| 300 |
"original_language": "eng_Latn",
|
| 301 |
"target_language": "ces_Latn",
|
| 302 |
"target_language_name": "Czech",
|
| 303 |
+
"speakers": 10700000,
|
| 304 |
"bleu": 68.6109083634317
|
| 305 |
},
|
| 306 |
{
|
|
|
|
| 308 |
"original_language": "eng_Latn",
|
| 309 |
"target_language": "ces_Latn",
|
| 310 |
"target_language_name": "Czech",
|
| 311 |
+
"speakers": 10700000,
|
| 312 |
"bleu": 59.72501366200287
|
| 313 |
},
|
| 314 |
{
|
|
|
|
| 316 |
"original_language": "eng_Latn",
|
| 317 |
"target_language": "ces_Latn",
|
| 318 |
"target_language_name": "Czech",
|
| 319 |
+
"speakers": 10700000,
|
| 320 |
"bleu": 60.25088578142904
|
| 321 |
}
|
| 322 |
]
|
results_summary.json
CHANGED
|
@@ -1,34 +1,42 @@
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
"target_language_name":"Banjar",
|
| 4 |
-
"bleu":29.2126571191
|
|
|
|
| 5 |
},
|
| 6 |
{
|
| 7 |
"target_language_name":"Bhojpuri",
|
| 8 |
-
"bleu":23.6476205243
|
|
|
|
| 9 |
},
|
| 10 |
{
|
| 11 |
"target_language_name":"Czech",
|
| 12 |
-
"bleu":65.4057381655
|
|
|
|
| 13 |
},
|
| 14 |
{
|
| 15 |
"target_language_name":"Icelandic",
|
| 16 |
-
"bleu":49.5636570439
|
|
|
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"target_language_name":"Indonesian",
|
| 20 |
-
"bleu":72.3220779959
|
|
|
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"target_language_name":"Kashmiri",
|
| 24 |
-
"bleu":10.772572222
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"target_language_name":"Lingala",
|
| 28 |
-
"bleu":21.2830292813
|
|
|
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"target_language_name":"Polish",
|
| 32 |
-
"bleu":59.3540779188
|
|
|
|
| 33 |
}
|
| 34 |
]
|
|
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
"target_language_name":"Banjar",
|
| 4 |
+
"bleu":29.2126571191,
|
| 5 |
+
"speakers":3500000.0
|
| 6 |
},
|
| 7 |
{
|
| 8 |
"target_language_name":"Bhojpuri",
|
| 9 |
+
"bleu":23.6476205243,
|
| 10 |
+
"speakers":52200000.0
|
| 11 |
},
|
| 12 |
{
|
| 13 |
"target_language_name":"Czech",
|
| 14 |
+
"bleu":65.4057381655,
|
| 15 |
+
"speakers":10700000.0
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"target_language_name":"Icelandic",
|
| 19 |
+
"bleu":49.5636570439,
|
| 20 |
+
"speakers":358000.0
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"target_language_name":"Indonesian",
|
| 24 |
+
"bleu":72.3220779959,
|
| 25 |
+
"speakers":198996550.0
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"target_language_name":"Kashmiri",
|
| 29 |
+
"bleu":10.772572222,
|
| 30 |
+
"speakers":6900000.0
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"target_language_name":"Lingala",
|
| 34 |
+
"bleu":21.2830292813,
|
| 35 |
+
"speakers":20000000.0
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"target_language_name":"Polish",
|
| 39 |
+
"bleu":59.3540779188,
|
| 40 |
+
"speakers":40200000.0
|
| 41 |
}
|
| 42 |
]
|