Sentiment-heb-Amram
Task Identifier: sentiment-2018-amram-heb
Cluster: Sentiment Analysis
Data Type: heb
Score Metric: Accuracy
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs InfoDCL
95.8
2
Finetuned LMs XLM-RoBERTa-Large
95.6
3
Finetuned LMs Bernice
95.4
4
Finetuned LMs XLM-RoBERTa-Base
95.2667
5
Finetuned LMs XLM-Twitter
94.8
6
Finetuned LMs TwHIN-BERT
94.6667
7
Finetuned LMs mBERT
93.2667
8
Zero-shot Chatgpt
84.2
9
Zero-shot mT0-XL
76.6
10
Zero-shot Bactrian-LLaMA-7B
75.8
11
Zero-shot BLOOMZ-P3-7B
71.2
12
Zero-shot BLOOMZ-7B
71
13
five-shot in-context learning mT0-XL
69
14
Baseline Majority
68.2476
15
Zero-shot LLaMA-7B
67
16
Zero-shot BLOOM-7B
64.8
17
three-shot in-context learning mT0-XL
63.6
18
Zero-shot Bactrian-BLOOM
60.8
19
five-shot in-context learning BLOOMZ-P3-7B
60.2
20
five-shot in-context learning LLaMA-7B
60
21
Zero-shot Chatgpt with translated prompts
58
22
three-shot in-context learning LLaMA-7B
56.4
23
three-shot in-context learning Vicuna-7B
56
24
five-shot in-context learning Vicuna-7B
54.4
25
three-shot in-context learning BLOOMZ-P3-7B
53.4
26
five-shot in-context learning BLOOM-7B
52.2
27
three-shot in-context learning BLOOM-7B
47.8
28
Baseline Random
47.6
29
Zero-shot Vicuna-7B
40.8
30
Zero-shot Alpaca-7B
34.8
31
three-shot in-context learning mT5-XL
32.8
32
five-shot in-context learning mT5-XL
32.2
33
Zero-shot mT5-XL
32.2