Add corpipe25-corefud1.3-large-251101 model.

README.md

@@ -0,0 +1,116 @@
+---
+license: cc-by-nc-sa-4.0
+language: [ca, cs, cu, de, en, es, fr, grc, hbo, hi, hu, ko, lt, no, pl, ru, tr]
+tags: [ CorPipe, CorPipe 25, CRAC Shared Task, CRAC 2025, CorefUD, CorefUD 1.3, Coreference Resolution, Minnt]
+base_model: google/mt5-large
+---
+
+# The `corpipe25-corefud1.3-large-251101` Model
+
+The `corpipe25-corefud1.3-large-251101` is a `mT5-large`-based multilingual model for
+coreference resolution usable in CorPipe 25 <https://github.com/ufal/crac2025-corpipe>.
+It is released on [LINDAT/CLARIAH-CZ](https://hdl.handle.net/11234/1-6079) and on
+[HuggingFace](https://huggingface.co/ufal/corpipe25-corefud1.3-large-251101) under the CC BY-NC-SA 4.0 license.
+The model is downloaded automatically from HuggingFace when running prediction with
+the `--load ufal/corpipe25-corefud1.3-large-251101` argument.
+
+The model is language agnostic, so it can be in theory used to predict
+coreference in any `mT5` language; for zero-shot cross-lingual evaluation,
+please refer to the CRAC 2025 paper.
+
+The model expects empty nodes to be already present on input, predicted by
+https://github.com/ufal/crac2025_empty_nodes_baseline.
+
+The model was trained using the following command (see the CorPipe 25 repository
+for more information):
+```sh
+tbs="ca_ancora cs_pcedt cs_pdt cu_proiel de_potsdamcc en_gum en_litbank es_ancora fr_ancor fr_democrat grc_proiel hbo_ptnk hi_hdtb hu_korkor hu_szegedkoref ko_ecmt lt_lcc no_bokmaalnarc no_nynorsknarc pl_pcc ru_rucor tr_itcc"
+
+python3 corpipe25.py --train --dev --treebanks $(for c in $tbs; do echo data/$c/$c-corefud-train.conllu; done) --batch_size=8 --learning_rate=6e-4 --learning_rate_decay  --adafactor --encoder=google/mt5-large --exp=corpipe25-corefud1.3-large --compile
+```
+
+
+## CorefUD 1.3 Test Sets Results
+
+The model achieves the following CorefUD 1.3 test set results (as reported in
+the paper); segment size 2560 was used, with the exception for `cu_proiel` and
+`grc_proiel` where it was 512:
+
+| avg   | ca    | cs_pce| cs_pdt| cu    | de_pot| en_gum| en_lit| es    | fr_anc| fr_dem| grc   | hbo_pt| hi    | hu_kor| hu_sze| ko_emc| lt    | no_bok| no_nyn| pl    | ru    | tr    |
+|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|
+| 72.84 | 80.1  | 74.6  | 78.0  | 58.5  | 67.2  | 73.3  | 77.4  | 82.0  | 72.1  | 68.5  | 71.2  | 67.9  | 76.3  | 67.3  | 68.0  | 69.8  | 74.4  | 75.2  | 74.0  | 77.5  | 81.2  | 67.7  |
+
+
+## Running the Model on Plain Text
+
+To run the model on plain text, first the plain text needs to be tokenized and
+converted to CoNLL-U (and optionally parsed if you also want mention heads),
+by using for example UDPipe 2:
+
+```sh
+curl -F data="Eve came home and Peter greeted her there. Then Peter and Paul set out to a trip and Eve waved them off." \
+  -F model=english -F tokenizer= -F tagger= -F parser=  https://lindat.mff.cuni.cz/services/udpipe/api/process \
+  | python -X utf8 -c "import sys,json; sys.stdout.write(json.load(sys.stdin)['result'])" >input.conllu
+```
+
+Then the CoNLL-U file can be processed by CorPipe 25, by using for example
+```sh
+python3 corpipe25.py --load ufal/corpipe25-corefud1.3-large-251101 --exp . --epoch 0 --test input.conllu
+```
+which would generate the following predictions in `input.00.conllu`:
+```
+# generator = UDPipe 2, https://lindat.mff.cuni.cz/services/udpipe
+# udpipe_model = english-ewt-ud-2.17-251125
+# udpipe_model_licence = CC BY-NC-SA
+# newdoc
+# global.Entity = eid-etype-head-other
+# newpar
+# sent_id = 1
+# text = Eve came home and Peter greeted her there.
+1	Eve	Eve	PROPN	NNP	Number=Sing	2	nsubj	_	Entity=(c1--1)
+2	came	come	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	0	root	_	_
+3	home	home	ADV	RB	_	2	advmod	_	Entity=(c2--1)
+4	and	and	CCONJ	CC	_	6	cc	_	_
+5	Peter	Peter	PROPN	NNP	Number=Sing	6	nsubj	_	Entity=(c3--1)
+6	greeted	greet	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	2	conj	_	_
+7	her	she	PRON	PRP	Case=Acc|Gender=Fem|Number=Sing|Person=3|PronType=Prs	6	obj	_	Entity=(c1--1)
+8	there	there	ADV	RB	PronType=Dem	6	advmod	_	Entity=(c2--1)|SpaceAfter=No
+9	.	.	PUNCT	.	_	2	punct	_	_
+
+# sent_id = 2
+# text = Then Peter and Paul set out to a trip and Eve waved them off.
+1	Then	then	ADV	RB	PronType=Dem	5	advmod	_	_
+2	Peter	Peter	PROPN	NNP	Number=Sing	5	nsubj	_	Entity=(c4--1(c3--1)
+3	and	and	CCONJ	CC	_	4	cc	_	_
+4	Paul	Paul	PROPN	NNP	Number=Sing	2	conj	_	Entity=(c5--1)c4)
+5	set	set	VERB	VBD	Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin	0	root	_	_
+6	out	out	ADP	RP	_	5	compound:prt	_	_
+7	to	to	ADP	IN	_	9	case	_	_
+8	a	a	DET	DT	Definite=Ind|PronType=Art	9	det	_	Entity=(c6--2
+9	trip	trip	NOUN	NN	Number=Sing	5	obl	_	Entity=c6)
+10	and	and	CCONJ	CC	_	12	cc	_	_
+11	Eve	Eve	PROPN	NNP	Number=Sing	12	nsubj	_	Entity=(c1--1)
+12	waved	wave	VERB	VBD	Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin	5	conj	_	_
+13	them	they	PRON	PRP	Case=Acc|Number=Plur|Person=3|PronType=Prs	12	obj	_	Entity=(c4--1)
+14	off	off	ADP	RP	_	12	compound:prt	_	SpaceAfter=No
+15	.	.	PUNCT	.	_	5	punct	_	SpaceAfter=No
+
+```
+
+## How to Cite
+
+```
+@inproceedings{straka-2025-corpipe,
+  title = "{C}or{P}ipe at {CRAC} 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution",
+  author = "Straka, Milan",
+  editor = "Ogrodniczuk, Maciej and Novak, Michal and Poesio, Massimo and Pradhan, Sameer and Ng, Vincent",
+  booktitle = "Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference",
+  month = nov,
+  year = "2025",
+  address = "Suzhou, China",
+  publisher = "Association for Computational Linguistics",
+  url = "https://aclanthology.org/2025.crac-1.11/",
+  doi = "10.18653/v1/2025.crac-1.11",
+  pages = "130--139",
+}
+```

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72072e9928d1379d5f30d9c6c44c7e7174c4e3556d5752b57d75bc77f80033e8
+size 2376264885

options.json

@@ -0,0 +1,49 @@
+{
+  "adafactor": true,
+  "batch_size": 8,
+  "compile": true,
+  "depth": 5,
+  "dev": [],
+  "encoder": "google/mt5-large",
+  "epochs": 15,
+  "exp": "mt5-large-s54",
+  "label_smoothing": 0.2,
+  "learning_rate": 0.0006,
+  "learning_rate_decay": true,
+  "load": [],
+  "logdir": "logs/mt5-large-s54-corpipe25--250624_153459-a=True,bs=8,c=True,d=5,d=,e=mt5-large,eb=10000,e=15,ls=0.2,lr=0.0006,lrd=True,r=50,se=0.5,sm=sentences,s=54,s=512,t=,t=True,t=ca_ancora-corefud-train.conllu,...,w=0.1",
+  "right": 50,
+  "sampling_exponent": 0.5,
+  "sampling_mode": "sentences",
+  "seed": 54,
+  "segment": 512,
+  "steps_per_epoch": 10000,
+  "test": [],
+  "threads": 8,
+  "train": true,
+  "treebanks": [
+    "data/ca_ancora/ca_ancora-corefud-train.conllu",
+    "data/cs_pcedt/cs_pcedt-corefud-train.conllu",
+    "data/cs_pdt/cs_pdt-corefud-train.conllu",
+    "data/cu_proiel/cu_proiel-corefud-train.conllu",
+    "data/de_potsdamcc/de_potsdamcc-corefud-train.conllu",
+    "data/en_gum/en_gum-corefud-train.conllu",
+    "data/en_litbank/en_litbank-corefud-train.conllu",
+    "data/es_ancora/es_ancora-corefud-train.conllu",
+    "data/fr_ancor/fr_ancor-corefud-train.conllu",
+    "data/fr_democrat/fr_democrat-corefud-train.conllu",
+    "data/grc_proiel/grc_proiel-corefud-train.conllu",
+    "data/hbo_ptnk/hbo_ptnk-corefud-train.conllu",
+    "data/hi_hdtb/hi_hdtb-corefud-train.conllu",
+    "data/hu_korkor/hu_korkor-corefud-train.conllu",
+    "data/hu_szegedkoref/hu_szegedkoref-corefud-train.conllu",
+    "data/ko_ecmt/ko_ecmt-corefud-train.conllu",
+    "data/lt_lcc/lt_lcc-corefud-train.conllu",
+    "data/no_bokmaalnarc/no_bokmaalnarc-corefud-train.conllu",
+    "data/no_nynorsknarc/no_nynorsknarc-corefud-train.conllu",
+    "data/pl_pcc/pl_pcc-corefud-train.conllu",
+    "data/ru_rucor/ru_rucor-corefud-train.conllu",
+    "data/tr_itcc/tr_itcc-corefud-train.conllu"
+  ],
+  "warmup": 0.1
+}

tags.txt

@@ -0,0 +1,56 @@
+
+POP:1
+POP:1,POP:1
+POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,POP:2,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:1,POP:2
+POP:1,POP:1,POP:1,POP:2,PUSH,POP:1
+POP:1,POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,POP:2
+POP:1,POP:1,POP:2,POP:2
+POP:1,POP:1,POP:2,PUSH,POP:1
+POP:1,POP:1,POP:3
+POP:1,POP:1,PUSH
+POP:1,POP:1,PUSH,POP:1
+POP:1,POP:1,PUSH,PUSH,POP:1
+POP:1,POP:2
+POP:1,POP:2,POP:2
+POP:1,POP:2,POP:2,POP:2
+POP:1,POP:2,PUSH,POP:1
+POP:1,POP:3,PUSH,POP:1
+POP:1,PUSH
+POP:1,PUSH,POP:1
+POP:1,PUSH,PUSH,POP:1
+POP:2
+POP:2,POP:2
+POP:2,POP:2,POP:2
+POP:2,POP:2,PUSH,POP:1
+POP:2,PUSH,POP:1
+POP:3
+POP:3,PUSH,POP:1
+POP:4
+PUSH
+PUSH,POP:1
+PUSH,PUSH
+PUSH,PUSH,POP:1
+PUSH,PUSH,PUSH
+PUSH,PUSH,PUSH,POP:1
+PUSH,PUSH,PUSH,PUSH
+PUSH,PUSH,PUSH,PUSH,POP:1
+PUSH,PUSH,PUSH,PUSH,PUSH
+PUSH,PUSH,PUSH,PUSH,PUSH,POP:1