Uni LMv1

GPTKB entity

Statements (59)
Predicate Object
gptkbp:instance_of gptkb:language
gptkbp:achieved_state_of_the_art various NLP benchmarks
gptkbp:application natural language processing
gptkbp:architecture gptkb:Transformers
gptkbp:can_be_fine_tuned gptkb:true
gptkbp:can_create coherent text
gptkbp:can_provide questions based on context
gptkbp:community_support gptkb:true
gptkbp:designed_for multi-task learning
gptkbp:developed_by gptkb:Microsoft_Research
gptkbp:evaluates BLEU score
ROUGE score
gptkbp:has_function 125 million
gptkbp:has_limitations computationally intensive
requires large datasets
may produce biased outputs
gptkbp:has_variants gptkb:Uni_LMv2
gptkb:Uni_LMv3
https://www.w3.org/2000/01/rdf-schema#label Uni LMv1
gptkbp:input_output text sequences
gptkbp:is_based_on gptkb:GPT_architecture
BERT architecture
gptkbp:is_cited_in gptkb:conference
research articles
academic papers
technical reports
theses
gptkbp:is_evaluated_by human annotators
automated metrics
gptkbp:is_influenced_by previous models
research advancements
gptkbp:is_open_source gptkb:true
gptkbp:is_part_of NLP research community
AI research community
Uni LM family
gptkbp:is_used_in language translation
chatbots
virtual assistants
content creation tools
gptkbp:language English
gptkbp:participated_in conversational AI
gptkbp:plot_summary long documents
gptkbp:pretraining_objective masked language modeling
gptkbp:provides_information_on large text corpora
gptkbp:release_year gptkb:2019
gptkbp:repository gptkb:Git_Hub
gptkbp:successor gptkb:Uni_LMv2
gptkbp:supports question answering
text generation
text summarization
dialog generation
gptkbp:training masked language modeling
sequence-to-sequence learning
gptkbp:type unsupervised learning model
gptkbp:uses transfer learning
self-attention mechanism
gptkbp:uses_positional_encoding gptkb:true
gptkbp:bfsParent gptkb:Uni_LM
gptkbp:bfsLayer 6