notesum.ai

Published at December 9

GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary

cs.CL

Released Date: December 9, 2024

Authors: Fatemah Almeman¹, Luis Espinosa-Anke

Aff.: ¹CardiffNLP, School of Computer Science and Informatics, Cardiff University, UK

Arxiv: http://arxiv.org/pdf/2412.06654v1

Refer to caption

Model/Method	Seen Definition			Unseen Definition			Description
Model/Method	mr	acc@k	rv	mr	acc@k	rv	mr	acc@k	rv
OneLook	0	66/.94/.95	200	-	-	-	5.5	.33/.54/.76	332
BOW	172	.03/.16/.43	414	248	.03/.13/.39	424	22	.13/.41/.69	308
RNN	134	.03/.16/.44	375	171	.03/.15/.42	404	17	.14/.40/.73	274
RDWECI	121	.06/.20/.44	420	170	.05/.19/.43	420	16	.14/.41/.74	306
SuperSense	378	.03/.15/.36	462	465	.02/.11/.31	454	115	.03/.15/.47	396
MS-LSTM	0	.92/.98/.99	65	276	.03/.14/.37	426	1000	.01/.04/.18	404
Multi-channel	16	.20/.44/.71	310	54	.09/.29/.58	358	2	.32/.64/.88	203
BERT	0	.57/.86/.92	240	18	.20/.46/.64	418	1	.36/.77/.94	94
RoBERTa	0	.57/.84/.92	228	37	.10/.36/.60	405	1	.43/.85/.96	46
GEAR_bp1	0	.66/.84/.96	200.122	0	.70/.88/.97	180.955	0	.89/.99/.99	70.5334
GEAR_bp2	0	.71/.88/.97	170.451	0	.65/.82/.95	225.324	0	.93/.99/1	1.57314
GEAR_rp	0	.70/.87/.96	185.97	0	.66/.86/.96	190.8	0	.91/.99/1	1.7837