Morpheme Segmentaiton On Unimorph 4 0

Metriken

f1 macro avg (subtask 2)

lev dist (subtask 2)

macro avg (subtask 1)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

				Paper Title
AUUH_B	89.77	3.50	-	Morfessor-enriched features and multilingual training for canonical morphological segmentation
AUUH_A	89.00	4.08	-	Morfessor-enriched features and multilingual training for canonical morphological segmentation
CLUZH-3	88.14	5.58	-	CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation
CLUZH-2	87.93	5.62	-	CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation
CLUZH-1	87.68	5.69	-	CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation
BiLSTM for seq labelling (Tü_Seg-2)	82.07	4.71	-	SIGMORPHON 2022 Shared Task on Morpheme Segmentation Submission Description: Sequence Labelling for Word-Level Morpheme Segmentation
AUUH_E	73.21	31.05	-	Morfessor-enriched features and multilingual training for canonical morphological segmentation
AUUH_D	72.75	36.38	-	Morfessor-enriched features and multilingual training for canonical morphological segmentation
AUUH_C	70.76	35.94	-	Morfessor-enriched features and multilingual training for canonical morphological segmentation
Bidirectional GRU + Morfessor features (AUUH_F)	66.73	36.35	93.72	Morfessor-enriched features and multilingual training for canonical morphological segmentation
Morfessor2	50.65	12.08	25.57	The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
ULM	45.99	14.28	20.61	The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
WordPiece	40.59	17.54	15.89	The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
BiLSTM for seq labelling (Tü_Seg-1)	-	-	96.06	SIGMORPHON 2022 Shared Task on Morpheme Segmentation Submission Description: Sequence Labelling for Word-Level Morpheme Segmentation
Char LSTM (DeepSPIN-2; soft-attention, 1-5 entmax)	-	-	97.15	Beyond Characters: Subword-level Morpheme Segmentation
HMM (JB132; trained w EM)	-	-	58.39	JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation
Ensemble of hard-attention transducers (CLUZH)	-	-	96.85	CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation
Subword-ULM transformer (DeepSPIN-3; soft-attention, 1-5 entmax)	-	-	97.29	Beyond Characters: Subword-level Morpheme Segmentation
Char LSTM (DeepSPIN-1; soft-attention)	-	-	96.32	Beyond Characters: Subword-level Morpheme Segmentation

0 of 19 row(s) selected.

Morpheme Segmentaiton On Unimorph 4 0 | SOTA | HyperAI