SOTAVerified

Morpheme Segmentaiton

Succesful systems segment a given word or sentence into a sequence of morphemes.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–6 of 6 papers

TitleStatusHype
Beyond Characters: Subword-level Morpheme Segmentation—0
CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection GenerationCode0
JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation—0
Morfessor-enriched features and multilingual training for canonical morphological segmentation—0
SIGMORPHON 2022 Shared Task on Morpheme Segmentation Submission Description: Sequence Labelling for Word-Level Morpheme Segmentation—0
The SIGMORPHON 2022 Shared Task on Morpheme SegmentationCode1
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Subword-ULM transformer (DeepSPIN-3; soft-attention, 1-5 entmax)macro avg (subtask 1)97.29—Unverified
2Char LSTM (DeepSPIN-2; soft-attention, 1-5 entmax)macro avg (subtask 1)97.15—Unverified
3Ensemble of hard-attention transducers (CLUZH)macro avg (subtask 1)96.85—Unverified
4Char LSTM (DeepSPIN-1; soft-attention)macro avg (subtask 1)96.32—Unverified
5BiLSTM for seq labelling (Tü_Seg-1)macro avg (subtask 1)96.06—Unverified
6Bidirectional GRU + Morfessor features (AUUH_F)macro avg (subtask 1)93.72—Unverified
7AUUH_Bf1 macro avg (subtask 2)89.77—Unverified
8AUUH_Af1 macro avg (subtask 2)89—Unverified
9CLUZH-3f1 macro avg (subtask 2)88.14—Unverified
10CLUZH-2f1 macro avg (subtask 2)87.93—Unverified