Merge branch 'add-jina' of https://github.com/KennethEnevoldsen/scand…

…inavian-embedding-benchmark into add-jina

src/seb/cache/jinaai__jina-embeddings-v3/Angry_Tweets.json

@@ -1 +1 @@
-{"task_name":"Angry Tweets","task_description":"A sentiment dataset with 3 classes (positiv, negativ, neutral) for Danish tweets","task_version":"1.1.1","time_of_run":"2024-11-13T21:33:16.042746","scores":{"da":{"accuracy":0.5680993314231136,"f1":0.5594053621774726,"accuracy_stderr":0.024346122584687404,"f1_stderr":0.022681854105695665,"main_score":0.5680993314231136}},"main_score":"accuracy"}
+{"task_name":"Angry Tweets","task_description":"A sentiment dataset with 3 classes (positiv, negativ, neutral) for Danish tweets","task_version":"1.1.1","time_of_run":"2024-12-11T22:07:20.690617","scores":{"da":{"accuracy":0.6091690544412608,"f1":0.6052343490049035,"accuracy_stderr":0.01654188475325484,"f1_stderr":0.015929005182812636,"main_score":0.6091690544412608}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/Bornholm_Parallel.json

@@ -1 +1 @@
-{"task_name":"Bornholm Parallel","task_description":"Danish Bornholmsk Parallel Corpus. Bornholmsk is a Danish dialect spoken on the island of Bornholm, Denmark. Historically it is a part of east Danish which was also spoken in Scania and Halland, Sweden.","task_version":"1.1.1","time_of_run":"2024-11-13T21:33:55.587815","scores":{"da":{"precision":0.3206724089635854,"recall":0.436,"f1":0.35174285714285713,"accuracy":0.436,"main_score":0.35174285714285713},"da-bornholm":{"precision":0.3206724089635854,"recall":0.436,"f1":0.35174285714285713,"accuracy":0.436,"main_score":0.35174285714285713}},"main_score":"f1"}
+{"task_name":"Bornholm Parallel","task_description":"Danish Bornholmsk Parallel Corpus. Bornholmsk is a Danish dialect spoken on the island of Bornholm, Denmark. Historically it is a part of east Danish which was also spoken in Scania and Halland, Sweden.","task_version":"1.1.1","time_of_run":"2024-12-11T22:08:05.312335","scores":{"da":{"precision":0.33535238095238096,"recall":0.45,"f1":0.3656333333333333,"accuracy":0.45,"main_score":0.3656333333333333},"da-bornholm":{"precision":0.33535238095238096,"recall":0.45,"f1":0.3656333333333333,"accuracy":0.45,"main_score":0.3656333333333333}},"main_score":"f1"}

src/seb/cache/jinaai__jina-embeddings-v3/DKHate.json

@@ -1 +1 @@
-{"task_name":"DKHate","task_description":"Danish Tweets annotated for Hate Speech either being Offensive or not","task_version":"1.1.1","time_of_run":"2024-11-13T22:19:50.826703","scores":{"da":{"accuracy":0.6477203647416412,"f1":0.5366895373219578,"ap":0.1795654122069819,"accuracy_stderr":0.06684788272628261,"f1_stderr":0.04571944298710895,"ap_stderr":0.0282077813963096,"main_score":0.6477203647416412}},"main_score":"accuracy"}
+{"task_name":"DKHate","task_description":"Danish Tweets annotated for Hate Speech either being Offensive or not","task_version":"1.1.1","time_of_run":"2024-12-11T22:09:29.031462","scores":{"da":{"accuracy":0.6787234042553191,"f1":0.5549690045301742,"ap":0.18587207926094124,"accuracy_stderr":0.07542711044895069,"f1_stderr":0.054513556188797,"ap_stderr":0.031926033464990976,"main_score":0.6787234042553191}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/Da_Political_Comments.json

@@ -1 +1 @@
-{"task_name":"Da Political Comments","task_description":"A dataset of Danish political comments rated for sentiment","task_version":"1.1.1","time_of_run":"2024-11-13T21:34:35.344272","scores":{"da":{"accuracy":0.4206437291897891,"f1":0.38642142217868036,"accuracy_stderr":0.027264394356405246,"f1_stderr":0.017817279657788544,"main_score":0.4206437291897891}},"main_score":"accuracy"}
+{"task_name":"Da Political Comments","task_description":"A dataset of Danish political comments rated for sentiment","task_version":"1.1.1","time_of_run":"2024-12-11T22:11:05.867373","scores":{"da":{"accuracy":0.4342397336293008,"f1":0.3998793870382494,"accuracy_stderr":0.025613002998655047,"f1_stderr":0.018941333655636754,"main_score":0.4342397336293008}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/DanFEVER.json

@@ -1 +1 @@
-{"task_name":"DanFEVER","task_description":"A Danish dataset intended for misinformation research. It follows the same format as the English FEVER dataset.","task_version":"1.1.1","time_of_run":"2024-11-13T21:36:36.608562","scores":{"da":{"ndcg_at_1":0.25859,"ndcg_at_3":0.34764,"ndcg_at_5":0.35958,"ndcg_at_10":0.36608,"ndcg_at_100":0.37129,"ndcg_at_1000":0.37169,"map_at_1":0.25851,"map_at_3":0.32666,"map_at_5":0.33333,"map_at_10":0.33608,"map_at_100":0.33722,"map_at_1000":0.33724,"recall_at_1":0.25851,"recall_at_3":0.40797,"recall_at_5":0.43676,"recall_at_10":0.45646,"recall_at_100":0.48015,"recall_at_1000":0.48313,"precision_at_1":0.25859,"precision_at_3":0.13604,"precision_at_5":0.0874,"precision_at_10":0.04568,"precision_at_100":0.00481,"precision_at_1000":0.00048,"mrr_at_1":0.25875,"mrr_at_3":0.32674,"mrr_at_5":0.33343,"mrr_at_10":0.33619,"mrr_at_100":0.3373,"mrr_at_1000":0.33732}},"main_score":"ndcg_at_10"}
+{"task_name":"DanFEVER","task_description":"A Danish dataset intended for misinformation research. It follows the same format as the English FEVER dataset.","task_version":"1.1.1","time_of_run":"2024-12-11T22:32:46.470067","scores":{"da":{"ndcg_at_1":0.31492,"ndcg_at_3":0.3914,"ndcg_at_5":0.39856,"ndcg_at_10":0.40282,"ndcg_at_100":0.40509,"ndcg_at_1000":0.40526,"map_at_1":0.31484,"map_at_3":0.37371,"map_at_5":0.37773,"map_at_10":0.37955,"map_at_100":0.38008,"map_at_1000":0.38009,"recall_at_1":0.31484,"recall_at_3":0.4421,"recall_at_5":0.45928,"recall_at_10":0.47215,"recall_at_100":0.48203,"recall_at_1000":0.48329,"precision_at_1":0.31492,"precision_at_3":0.14744,"precision_at_5":0.09192,"precision_at_10":0.04726,"precision_at_100":0.00483,"precision_at_1000":0.00048,"mrr_at_1":0.31492,"mrr_at_3":0.37374,"mrr_at_5":0.37777,"mrr_at_10":0.37956,"mrr_at_100":0.38009,"mrr_at_1000":0.3801}},"main_score":"ndcg_at_10"}

src/seb/cache/jinaai__jina-embeddings-v3/LCC.json

@@ -1 +1 @@
-{"task_name":"LCC","task_description":"The leipzig corpora collection, annotated for sentiment","task_version":"1.1.1","time_of_run":"2024-11-14T13:57:48.545664","scores":{"da":{"accuracy":0.5999999999999999,"f1":0.5885173430161176,"accuracy_stderr":0.03055050463303893,"f1_stderr":0.02601687642478716,"main_score":0.5999999999999999}},"main_score":"accuracy"}
+{"task_name":"LCC","task_description":"The leipzig corpora collection, annotated for sentiment","task_version":"1.1.1","time_of_run":"2024-12-11T22:03:21.013601","scores":{"da":{"accuracy":0.616,"f1":0.6156757118925441,"accuracy_stderr":0.033359989341858146,"f1_stderr":0.029531773504062154,"main_score":0.616}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/Language_Identification.json

@@ -1 +1 @@
-{"task_name":"Language Identification","task_description":"A dataset for Nordic language identification.","task_version":"1.1.1","time_of_run":"2024-11-13T21:50:33.466847","scores":{"da":{"accuracy":0.48129999999999995,"f1":0.4716944543998669,"accuracy_stderr":0.012093570376214148,"f1_stderr":0.013172338407872259,"main_score":0.48129999999999995},"sv":{"accuracy":0.48129999999999995,"f1":0.4716944543998669,"accuracy_stderr":0.012093570376214148,"f1_stderr":0.013172338407872259,"main_score":0.48129999999999995},"nb":{"accuracy":0.48129999999999995,"f1":0.4716944543998669,"accuracy_stderr":0.012093570376214148,"f1_stderr":0.013172338407872259,"main_score":0.48129999999999995},"nn":{"accuracy":0.48129999999999995,"f1":0.4716944543998669,"accuracy_stderr":0.012093570376214148,"f1_stderr":0.013172338407872259,"main_score":0.48129999999999995},"is":{"accuracy":0.48129999999999995,"f1":0.4716944543998669,"accuracy_stderr":0.012093570376214148,"f1_stderr":0.013172338407872259,"main_score":0.48129999999999995},"fo":{"accuracy":0.48129999999999995,"f1":0.4716944543998669,"accuracy_stderr":0.012093570376214148,"f1_stderr":0.013172338407872259,"main_score":0.48129999999999995}},"main_score":"accuracy"}
+{"task_name":"Language Identification","task_description":"A dataset for Nordic language identification.","task_version":"1.1.1","time_of_run":"2024-12-13T16:27:56.414291","scores":{"da":{"accuracy":0.4083333333333333,"f1":0.3925482204639472,"accuracy_stderr":0.008633268983029165,"f1_stderr":0.007916299274783293,"main_score":0.4083333333333333},"sv":{"accuracy":0.4083333333333333,"f1":0.3925482204639472,"accuracy_stderr":0.008633268983029165,"f1_stderr":0.007916299274783293,"main_score":0.4083333333333333},"nb":{"accuracy":0.4083333333333333,"f1":0.3925482204639472,"accuracy_stderr":0.008633268983029165,"f1_stderr":0.007916299274783293,"main_score":0.4083333333333333},"nn":{"accuracy":0.4083333333333333,"f1":0.3925482204639472,"accuracy_stderr":0.008633268983029165,"f1_stderr":0.007916299274783293,"main_score":0.4083333333333333},"is":{"accuracy":0.4083333333333333,"f1":0.3925482204639472,"accuracy_stderr":0.008633268983029165,"f1_stderr":0.007916299274783293,"main_score":0.4083333333333333},"fo":{"accuracy":0.4083333333333333,"f1":0.3925482204639472,"accuracy_stderr":0.008633268983029165,"f1_stderr":0.007916299274783293,"main_score":0.4083333333333333}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/Massive_Intent.json

@@ -1 +1 @@
-{"task_name":"Massive Intent","task_description":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","task_version":"1.1.1","time_of_run":"2024-11-13T21:43:34.445063","scores":{"da":{"accuracy":0.6379959650302622,"f1":0.6031210839216415,"accuracy_stderr":0.018687738234453372,"f1_stderr":0.01601335989279753,"main_score":0.6379959650302622},"nb":{"accuracy":0.6341627437794217,"f1":0.6000839733610837,"accuracy_stderr":0.016888194867408664,"f1_stderr":0.017814875436374125,"main_score":0.6341627437794217},"sv":{"accuracy":0.6594821788836583,"f1":0.6323874307279661,"accuracy_stderr":0.022018459492548024,"f1_stderr":0.017138250345814364,"main_score":0.6594821788836583}},"main_score":"accuracy"}
+{"task_name":"Massive Intent","task_description":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","task_version":"1.1.1","time_of_run":"2024-12-13T12:30:27.747355","scores":{"da":{"accuracy":0.7229993275050437,"f1":0.6777312864344521,"accuracy_stderr":0.021605725550200672,"f1_stderr":0.019667189317759903,"main_score":0.7229993275050437},"nb":{"accuracy":0.7127437794216543,"f1":0.6693877898238115,"accuracy_stderr":0.014615011239315112,"f1_stderr":0.012458761208978947,"main_score":0.7127437794216543},"sv":{"accuracy":0.731102891728312,"f1":0.6918924054876893,"accuracy_stderr":0.021828159697349376,"f1_stderr":0.02278756069148256,"main_score":0.731102891728312}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/Massive_Scenario.json

@@ -1 +1 @@
-{"task_name":"Massive Scenario","task_description":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","task_version":"1.1.1","time_of_run":"2024-11-13T21:46:44.729375","scores":{"da":{"accuracy":0.7350706119704102,"f1":0.7264571146442774,"accuracy_stderr":0.007798404730966382,"f1_stderr":0.009457832203659417,"main_score":0.7350706119704102},"nb":{"accuracy":0.7190988567585743,"f1":0.7119164347268657,"accuracy_stderr":0.01014353370687806,"f1_stderr":0.010327527565859801,"main_score":0.7190988567585743},"sv":{"accuracy":0.7415265635507734,"f1":0.7321277292640845,"accuracy_stderr":0.009021276077818262,"f1_stderr":0.009842616330101132,"main_score":0.7415265635507734}},"main_score":"accuracy"}
+{"task_name":"Massive Scenario","task_description":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","task_version":"1.1.1","time_of_run":"2024-12-13T16:04:24.007081","scores":{"da":{"accuracy":0.8303967720242097,"f1":0.8144907891114421,"accuracy_stderr":0.01345679043361314,"f1_stderr":0.012214051749594796,"main_score":0.8303967720242097},"nb":{"accuracy":0.8227303295225286,"f1":0.809055319974268,"accuracy_stderr":0.01164970138337166,"f1_stderr":0.010758393028445808,"main_score":0.8227303295225286},"sv":{"accuracy":0.8377269670477471,"f1":0.8214039898309877,"accuracy_stderr":0.011274273146386207,"f1_stderr":0.010311356519461268,"main_score":0.8377269670477471}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/NoReC.json

@@ -1 +1 @@
-{"task_name":"NoReC","task_description":"A Norwegian dataset for sentiment classification on review","task_version":"1.1.1","time_of_run":"2024-11-13T21:51:14.423683","scores":{"nb":{"accuracy":0.5984375,"f1":0.5772198167649724,"accuracy_stderr":0.018554944488351894,"f1_stderr":0.01755204684778349,"main_score":0.5984375}},"main_score":"accuracy"}
+{"task_name":"NoReC","task_description":"A Norwegian dataset for sentiment classification on review","task_version":"1.1.1","time_of_run":"2024-12-13T16:29:32.719809","scores":{"nb":{"accuracy":0.61494140625,"f1":0.5977866105449843,"accuracy_stderr":0.030842373184347828,"f1_stderr":0.02791508266619411,"main_score":0.61494140625}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/Norwegian_courts.json

@@ -1 +1 @@
-{"task_name":"Norwegian courts","task_description":"Nynorsk and Bokmål parallel corpus from Norwegian courts. Norway has two standardised written languages. Bokmål is a variant closer to Danish, while Nynorsk was created to resemble regional dialects of Norwegian.","task_version":"1.1.1","time_of_run":"2024-11-13T21:52:11.201687","scores":{"nb":{"precision":0.9049707602339182,"recall":0.9298245614035088,"f1":0.9130116959064327,"accuracy":0.9298245614035088,"main_score":0.9130116959064327},"nn":{"precision":0.9049707602339182,"recall":0.9298245614035088,"f1":0.9130116959064327,"accuracy":0.9298245614035088,"main_score":0.9130116959064327}},"main_score":"f1"}
+{"task_name":"Norwegian courts","task_description":"Nynorsk and Bokmål parallel corpus from Norwegian courts. Norway has two standardised written languages. Bokmål is a variant closer to Danish, while Nynorsk was created to resemble regional dialects of Norwegian.","task_version":"1.1.1","time_of_run":"2024-12-13T16:36:58.457846","scores":{"nb":{"precision":0.9203216374269007,"recall":0.9385964912280702,"f1":0.9261695906432749,"accuracy":0.9385964912280702,"main_score":0.9261695906432749},"nn":{"precision":0.9203216374269007,"recall":0.9385964912280702,"f1":0.9261695906432749,"accuracy":0.9385964912280702,"main_score":0.9261695906432749}},"main_score":"f1"}

src/seb/cache/jinaai__jina-embeddings-v3/Norwegian_parliament.json

@@ -1 +1 @@
-{"task_name":"Norwegian parliament","task_description":"Norwegian parliament speeches annotated with the party of the speaker (`Sosialistisk Venstreparti` vs `Fremskrittspartiet`)","task_version":"1.1.1","time_of_run":"2024-11-13T21:52:00.593689","scores":{"nb":{"accuracy":0.6006666666666666,"f1":0.598941034068567,"ap":0.5607351566727996,"accuracy_stderr":0.018195695461656135,"f1_stderr":0.019486204000061156,"ap_stderr":0.013099108893732402,"main_score":0.6006666666666666}},"main_score":"accuracy"}
+{"task_name":"Norwegian parliament","task_description":"Norwegian parliament speeches annotated with the party of the speaker (`Sosialistisk Venstreparti` vs `Fremskrittspartiet`)","task_version":"1.1.1","time_of_run":"2024-12-14T15:36:28.812275","scores":{"nb":{"accuracy":0.5688333333333333,"f1":0.5652299805603136,"ap":0.5401466909214766,"accuracy_stderr":0.026199554703595005,"f1_stderr":0.02768317419649942,"ap_stderr":0.01711798949729587,"main_score":0.5688333333333333}},"main_score":"accuracy"}

src/seb/cache/jinaai__jina-embeddings-v3/SNL_Clustering.json

@@ -1 +1 @@
-{"task_name":"SNL Clustering","task_description":"Webscrabed articles from the Norwegian lexicon 'Det Store Norske Leksikon'. Uses articles categories as clusters.","task_version":"0.0.1","time_of_run":"2024-11-13T21:54:10.329920","scores":{"nb":{"v_measure":0.5957282278588,"v_measure_std":0.014688046062978624}},"main_score":"v_measure"}
+{"task_name":"SNL Clustering","task_description":"Webscrabed articles from the Norwegian lexicon 'Det Store Norske Leksikon'. Uses articles categories as clusters.","task_version":"0.0.1","time_of_run":"2024-12-14T19:34:35.710300","scores":{"nb":{"v_measure":0.6868723955917873,"v_measure_std":0.009034855336828941}},"main_score":"v_measure"}