Ilker Kesen commited on
Commit
7987659
1 Parent(s): 489c22a

update results

Browse files
app.py CHANGED
@@ -44,6 +44,7 @@ def cache_datasets(path):
44
  datasets = json.load(f)
45
  for key in datasets.keys():
46
  datasets[key]['dataset'] = key
 
47
  return datasets
48
 
49
 
 
44
  datasets = json.load(f)
45
  for key in datasets.keys():
46
  datasets[key]['dataset'] = key
47
+ del datasets['tr-wikihow-summ'] # FIXME: There are missing experiments.
48
  return datasets
49
 
50
 
data/datasets.json CHANGED
@@ -48,7 +48,7 @@
48
  "generative": true
49
  },
50
  "tr-wikihow-summ": {
51
- "name": "WikiHowSumm",
52
  "task": "summarization",
53
  "description": "A summarization dataset obtained from WikiHow website.",
54
  "url": "https://huggingface.co/datasets/ardauzunoglu/tr-wikihow-summ",
 
48
  "generative": true
49
  },
50
  "tr-wikihow-summ": {
51
+ "name": "WikiHow",
52
  "task": "summarization",
53
  "description": "A summarization dataset obtained from WikiHow website.",
54
  "url": "https://huggingface.co/datasets/ardauzunoglu/tr-wikihow-summ",
results/zero-shot/aya-23-8b.json CHANGED
@@ -150,6 +150,13 @@
150
  "wer": 0.7464128097803795,
151
  "bleu": 0.16878189334002527
152
  },
 
 
 
 
 
 
 
153
  {
154
  "name": "xlsum_tr",
155
  "task": "summarization",
 
150
  "wer": 0.7464128097803795,
151
  "bleu": 0.16878189334002527
152
  },
153
+ {
154
+ "name": "tr-wikihow-summ",
155
+ "task": "summarization",
156
+ "rouge1": 0.04023948542641836,
157
+ "rouge2": 0.0169810919324388,
158
+ "rougeL": 0.03296869279651223
159
+ },
160
  {
161
  "name": "xlsum_tr",
162
  "task": "summarization",
results/zero-shot/kanarya-2b.json CHANGED
@@ -157,9 +157,9 @@
157
  {
158
  "name": "tr-wikihow-summ",
159
  "task": "summarization",
160
- "rouge1": null,
161
- "rouge2": null,
162
- "rougeL": null
163
  },
164
  {
165
  "name": "xquad_tr",
 
157
  {
158
  "name": "tr-wikihow-summ",
159
  "task": "summarization",
160
+ "rouge1": 0.18320144404095734,
161
+ "rouge2": 0.05292686441577856,
162
+ "rougeL": 0.13617779525430102
163
  },
164
  {
165
  "name": "xquad_tr",
results/zero-shot/llama-3.1-8b-instruct.json CHANGED
@@ -126,34 +126,41 @@
126
  {
127
  "name": "gecturk_generation",
128
  "task": "grammatical_error_correction",
129
- "exact_match": 0.005007463045885695
130
  },
131
  {
132
  "name": "mlsum_tr",
133
  "task": "summarization",
134
- "rouge1": 0.40612528796779146,
135
- "rouge2": 0.25769550481564407,
136
- "rougeL": 0.3281187592669974
 
 
 
 
 
 
 
137
  },
138
  {
139
  "name": "wiki_lingua_tr",
140
  "task": "summarization",
141
- "rouge1": 0.23621778991663983,
142
- "rouge2": 0.08052321922363763,
143
- "rougeL": 0.1710165526266978
144
  },
145
  {
146
  "name": "wmt-tr-en-prompt",
147
  "task": "machine_translation",
148
- "wer": 0.823814082821166,
149
- "bleu": 0.13572050882587958
150
  },
151
  {
152
  "name": "xlsum_tr",
153
  "task": "summarization",
154
- "rouge1": 0.29619456321037296,
155
- "rouge2": 0.13520487191226377,
156
- "rougeL": 0.220446635816053
157
  }
158
  ]
159
  }
 
126
  {
127
  "name": "gecturk_generation",
128
  "task": "grammatical_error_correction",
129
+ "exact_match": 0.006548220906158217
130
  },
131
  {
132
  "name": "mlsum_tr",
133
  "task": "summarization",
134
+ "rouge1": 0.3970732593089523,
135
+ "rouge2": 0.2580847974481608,
136
+ "rougeL": 0.32541870004323864
137
+ },
138
+ {
139
+ "name": "tr-wikihow-summ",
140
+ "task": "summarization",
141
+ "rouge1": 0.2444219472309469,
142
+ "rouge2": 0.07918689923056912,
143
+ "rougeL": 0.1723711997990579
144
  },
145
  {
146
  "name": "wiki_lingua_tr",
147
  "task": "summarization",
148
+ "rouge1": 0.22962802442673436,
149
+ "rouge2": 0.07863769381205138,
150
+ "rougeL": 0.16924353815052512
151
  },
152
  {
153
  "name": "wmt-tr-en-prompt",
154
  "task": "machine_translation",
155
+ "wer": 0.7815049287082738,
156
+ "bleu": 0.1564145890661644
157
  },
158
  {
159
  "name": "xlsum_tr",
160
  "task": "summarization",
161
+ "rouge1": 0.2805962791068744,
162
+ "rouge2": 0.12421139697660691,
163
+ "rougeL": 0.21080710839195932
164
  }
165
  ]
166
  }
results/zero-shot/llama-3.1-8b.json CHANGED
@@ -122,6 +122,45 @@
122
  "task": "extractive_question_answering",
123
  "exact_match": 0.2092436974789916,
124
  "f1": 0.35674599908781446
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
125
  }
126
  ]
127
  }
 
122
  "task": "extractive_question_answering",
123
  "exact_match": 0.2092436974789916,
124
  "f1": 0.35674599908781446
125
+ },
126
+ {
127
+ "name": "gecturk_generation",
128
+ "task": "grammatical_error_correction",
129
+ "exact_match": 0.006548220906158217
130
+ },
131
+ {
132
+ "name": "mlsum_tr",
133
+ "task": "summarization",
134
+ "rouge1": 0.3970732593089523,
135
+ "rouge2": 0.2580847974481608,
136
+ "rougeL": 0.32541870004323864
137
+ },
138
+ {
139
+ "name": "tr-wikihow-summ",
140
+ "task": "summarization",
141
+ "rouge1": 0.2444219472309469,
142
+ "rouge2": 0.07918689923056912,
143
+ "rougeL": 0.1723711997990579
144
+ },
145
+ {
146
+ "name": "wiki_lingua_tr",
147
+ "task": "summarization",
148
+ "rouge1": 0.22962802442673436,
149
+ "rouge2": 0.07863769381205138,
150
+ "rougeL": 0.16924353815052512
151
+ },
152
+ {
153
+ "name": "wmt-tr-en-prompt",
154
+ "task": "machine_translation",
155
+ "wer": 0.7815049287082738,
156
+ "bleu": 0.1564145890661644
157
+ },
158
+ {
159
+ "name": "xlsum_tr",
160
+ "task": "summarization",
161
+ "rouge1": 0.2805962791068744,
162
+ "rouge2": 0.12421139697660691,
163
+ "rougeL": 0.21080710839195932
164
  }
165
  ]
166
  }