|
gptkbp:instanceOf
|
large language model
|
|
gptkbp:author
|
gptkb:Sebastian_Riedel
gptkb:Patrick_Lewis
gptkb:Fabio_Petroni
gptkb:Tim_Rocktäschel
gptkb:Yuxiang_Wu
Alexander H. Miller
Anton Bakhtin
|
|
gptkbp:category
|
NLP evaluation benchmark
|
|
gptkbp:contains
|
gptkb:SQuAD_dataset
Cloze questions
ConceptNet dataset
Google-RE dataset
T-REx dataset
|
|
gptkbp:developedBy
|
gptkb:Facebook_AI_Research
|
|
gptkbp:fullName
|
LAnguage Model Analysis
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
LAMA
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
gptkb:MIT_License
|
|
gptkbp:notablePublication
|
LAMA: Open-world Knowledge Probing
https://arxiv.org/abs/1909.01066
|
|
gptkbp:publishedIn
|
gptkb:EMNLP_2019
|
|
gptkbp:purpose
|
probe factual knowledge in language models
|
|
gptkbp:relatedTo
|
gptkb:GPT-2
gptkb:BERT
gptkb:RoBERTa
gptkb:XLNet
|
|
gptkbp:releaseYear
|
2019
|
|
gptkbp:usedFor
|
evaluating knowledge in pretrained language models
|
|
gptkbp:bfsParent
|
gptkb:Laboratoire_d'Analyse_et_de_Mathématiques_Appliquées
gptkb:Library_Administration_and_Management_Association
|
|
gptkbp:bfsLayer
|
7
|