new repo structure

.gitignore

@@ -1,3 +1,16 @@
 .ipynb_checkpoints
 data/
 ud/
+stanza_old/
+old/
+*_old.*
+.vscode
+
+# Python junk
+__pycache__/
+*.pyc
+
+# Images / binaries (HF blocks these)
+*.png
+*.gif
+*.ttf

README.md

@@ -1,3 +1,15 @@
+---
+language: 
+  - se
+thumbnail: "https://www.uu.se/images/18.719e0b6018d874d37f14fa91/1708853093133/DigPhilBild.png"
+tags:
+- stanza
+- historical
+- digphil
+base_model: "KBLab/bert-base-swedish-cased"
+library_name: stanza
+---
+
 # Retraining Stanza to optimize depparse on a diachronic Swedish corpus
 
 This repository contains forked code from the official Stanza github, with scripts that help prepare for and train models on different combinations of treebanks relevant to historical Swedish. 

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-letter141673-Stalhammar.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7122b90c2a556ecfea05b519b674c4ac5d7674109f3ac3e8ff9a14016d4f7be7
-size 4861995
+oid sha256:57b5c7d338208146eff776e763c968ae12d0963dc4833b6b14fbf6e279e813b3
+size 3706104

alanev_raw_files/{newly-parsed-diachron-v2/svediakorp-letter141673-Stalhammar_preprocessed.conllu → 11_files_normalized_conllu/svediakorp-letter141677-linnebreven.conllu}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89198cd3515f9cac2525b51153aaaa2060dc56427272bea2b39245a8e94feda8
-size 16081
+oid sha256:84bd3cefcc221d7a5ccf17d54a44b7ac23baa3ba8c46ed1adb18a304745e29e2
+size 9718114

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec1108-spf265.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d86755dfc616264bc63183b0c9bfe2eb51d0691deb6dee429d8cc2e5d0b9b1
-size 1313864
+oid sha256:823e1e7f511beb9ec674685feb8c7f159802da2085346b06fa0e9b7ca235bf22
+size 1022502

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec208-Anonym_DetGrasligaMordet.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7396134baa99f160d5be6662860d388119cfb0635eda5a639980e7e2aa9e2b
-size 604646
+oid sha256:e5cd00de7a4f7d236f5b836da0465443ef5931761ef1f9830769bc4b66f3dad5
+size 466861

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec268-DulciU_VitterhetsNojen3.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66cdf530ed97c173bef984328ed686533de60c6bc7dcabb65dac99eb58ea0a81
-size 2427818
+oid sha256:935ea7c8a5af66ce870a5d7a3d444302c4eca9a48ec8b57f15355993a81b8ff9
+size 1852411

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec324-GranbergPA_Enslighetsalskaren.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed169681fb83845b7d71daa22554ea7fa77096c53a3c959675bc777e46614bb3
-size 1746605
+oid sha256:4164f1785b9a2f96a04715644dcb40d277e5b1684c5329da06501b3cb43372c0
+size 1360129

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec397-AngeredStrandbergH_UnderSodernsSol.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d22db7a114e117f6aa66c91990dbb7c5ffdba666f74c26c7b59a4fd52d279ca
-size 3004999
+oid sha256:5ceb469039ffd186c2fc1b1eac33caf1aaf8c374a2d0f658f4ea121d8d8afd8a
+size 2315941

{ud-treebanks-sv → alanev_raw_files/11_files_normalized_conllu}/svediakorp-sec486-SchwartzMS_BellmansSkor.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b76dafbea7a70ea546d2602f240890288f5b4dbd80593082a775d0adc925799
-size 8752
+oid sha256:ee4fecf19a8829fb94ed22bcb75cab36694aff3714ea7072348e51dc97386d89
+size 787701

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec987-spf144.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5605015346ca79045d55eb5c7ffd70ff0cbd9025a052e9eecef314c029ad8769
-size 161143
+oid sha256:11cae0b7b3e9747490c1a2d03b472e794ab92a22b1ddfd027569f87c7ab82b34
+size 126678

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec988-spf145.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76bc1db11e328e2534f38145464bfc46f41382f40e20d32d52c08c25f01e0599
-size 1730441
+oid sha256:5c94be84afc9f15ed65a1b7111dbc91830721942844033372c43879ec898d863
+size 1363502

alanev_raw_files/{newly-parsed-diachron-v2 → 11_files_normalized_conllu}/svediakorp-sec991-spf148.conllu

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2ba762eb5091b388bf89299e468e09d37ac635ce563c487d625686dac3cf46
-size 150781
+oid sha256:5be53ffccdd2d99658fc0884caba246ad334db49b8dfbe07482362d8b1d8fd85
+size 121388

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1031-spf188.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:165b57f03a0e3b7c93e55ba547fe6018ba700f3b0f28aca4bdbb797308fb925b
-size 1786389

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1033-spf190.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7bcbb52d399cf7c42d0a45a8bf3de912403c2e0215ddc5e3222a1ed33372d6e6
-size 3532440

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1033-spf190_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b018233f75812f754ffa4af3df1c6e4c6b55fc966de3e5f0fe7f854e3ee996e1
-size 12725

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1063-spf220.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc13fa7db162d0fba51d8bf9429288e3204bcbf436f13b5ff218c656d57abc82
-size 1352619

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1063-spf220_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5c260d6007081916c93837625dfef7527b1ac29c1d36f43a55cafc009d50f436
-size 15321

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1102-spf259.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9fd8227eeb0dbbbdd1f3a1b9d1825a58ccb1bcbc50e04a1f4495294e109cfff5
-size 1488289

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec1102-spf259_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fab3c9d5672c63904a8d34c4f009207cd5af62b2c47ce18debaae60d9150d4fc
-size 18561

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec192-1732-BrennerSE_PoetiskeDikter2.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ccd4c0571a0502c6cdb4582005a8ccf6a6358a21bf06d21d230787d0f1263615
-size 3127677

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec208-Anonym_DetGrasligaMordet_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b8683091284fa92dca00338179b7fe57ce1d68e9deb57d69526924a23dcb4c87
-size 9991

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec25-Runius.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a23ebade9965b682a507908a9d0a24096091fe8ed492ae78c158ff347af5931
-size 3262165

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec25-Runius_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e00fbc651e8749ae0467ded05e04b4caabcd56315eb725bff43d6c268e5298d1
-size 5136

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec252-BremerF_Teckningar1.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76e3d17de74f9e9e52da5fa002d97820cfdbbae88bda89d217d9f12eb9ca0e52
-size 3455332

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec252-BremerF_Teckningar1_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f91f3385edcd313a7d8e75a80c516e1f2523131b8e59590c71a38270e4b41247
-size 5493

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec254-CederborghF_BerattelseOmJohnHall.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e693658652cafa1a51fe8ac1546867a6c45bde638d8f0620671df6be3a67021
-size 346450

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec254-CederborghF_BerattelseOmJohnHall_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:64acc8612fd640fd83637704a859b7a7f7b8267b76a37ad57befb3749a6e94f3
-size 24530

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec267-DulciU_VitterhetsNojen2.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94852fb0fb23aa7ff49a741d90c418974d8cfdb72d3095f7b4493fe7041ec562
-size 1757555

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec268-DulciU_VitterhetsNojen3_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9b982c8ad515bce92fe80f946604338bbd2cf01205d7a2917f8596dd72a1d954
-size 64766

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec277-EnbomPU_MedborgeligtSkalde.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e8b98dd2bb0d9a6241d72142a64de48300521f25ee16fec435e9f5248158666
-size 947528

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec277-EnbomPU_MedborgeligtSkalde_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d5ed4fc6cfbe8ee0e45ea51aa33803e706da05fbf19c826b63aead6ec08dfde4
-size 24068

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec306-FrodingG_RagglerAPaschaserI.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ee2a043c74153d0a4dbf218a2033285fae29fbb229e1f7f4bb18388949c17
-size 1212400

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec307-FrodingG_RagglerAPaschaserII.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95ae82f664d719196d57e9ea4d961e1376a814be1103e5edf3015ef763af6e31
-size 778126

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec324-GranbergPA_Enslighetsalskaren_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a5027bdb3d9498a16969e723f984b716a28e1e6f268dee6861dfd0c8893ed0b
-size 13851

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec330-GyllenborgC_SwenskaSpratthoken.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:229c5d4f5dc1e02e43a5c06fe103b72b4c20b927ea26d66419f3246003e5ec7c
-size 3325076

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec330-GyllenborgC_SwenskaSpratthoken_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b4e80fb5fd35bd2dcb43ac4e2b07ca2c91546b47792a6e219096519bf576f62a
-size 34449

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec339-HanssonO_LiteraraSilhouetter.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ab31a6b38e2dbcb006ff205417caa023b32fdef9a639103c7b308343baa84730
-size 3018951

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec397-AngeredStrandbergH_UnderSodernsSol_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a8bb05fc63f67b268e5b651928279e07e2ba3d606986b37d537c7467c5f7d6a2
-size 19312

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec415-LevertinO_PepitasBrollop.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a52cbeda826709ecf327c072846aedc5d00f8fa4a3b1e94cc90fd9031b4b89aa
-size 876269

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec452-NyblomH_FantasierFyra.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eee74604663d7b6cebbc61404d87dfa7f011dea94db926e4d62c433972bbb531
-size 2023495

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec452-NyblomH_FantasierFyra_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a848e73e35cd9e020dde1741d2b05d821829b98a6e6b629c728455ceb37d2a59
-size 18739

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec486-SchwartzMS_BellmansSkor_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b78b4b3f01515dab3004f52a218a7ee5d7ce584f76225d3fefba3efa3744f09
-size 11952

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec492-SchwartzMS_PaGothakanal.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ac98aaf031651efc3de4b1add3fca89ac5e540c336759270d1a603d58b58c418
-size 1692192

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec494-SchwerinM_SmasakerAfEn1.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e076abaa417e1232799a5c91475b48cd3e3be80c49bae2a897ceb131a9d4209e
-size 2444502

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec519-StrandbergCG_EsaiasTegner1853.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9f150e830fe0abfd39d3df78b911a697e1b04405cc8d074e24fb82e179a2b336
-size 198165

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec545-WallinJO_Vitterhetsforsok.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6111d6345506648abb38c44219ac553bdf451289e0da832c62f52de8943a435e
-size 4000480

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec609-EngstromA_GenomMinaGuldbagadeGlasogon.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17497c47ed0832459629d2ed341261c3a2ab7f18caf09c4885777e116662926e
-size 4045144

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec613-EngstromA_StrindbergOchJag.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04da710d54e80bc26784dbc9e3a0c6d54c1fc89b2246ac79a5479091e77fa4a4
-size 1371374

alanev_raw_files/newly-parsed-diachron-v2/svediakorp-sec613-EngstromA_StrindbergOchJag_preprocessed.conllu

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cf85da9fa0effbf282a8e6e99c76bdf06442716df10771ffa8f2264d1294a529
-size 13950