142,611
edits
(Created page with "== Introduction == BERT, or Bidirectional Encoder Representations from Transformers, is a transformer-based machine learning technique for natural language processing (NLP). It is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As such, the pre-trained BERT model can be fine-tuned with just one additi...") |
No edit summary |
||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
BERT, or Bidirectional Encoder Representations from Transformers, is a [[Transformer (machine learning model)|transformer-based]] machine learning technique for [[Natural language processing|natural language processing]] (NLP). It is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As such, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. | BERT, or Bidirectional Encoder Representations from Transformers, is a [[Transformer (machine learning model)|transformer-based]] machine learning technique for [[Natural language processing|natural language processing]] (NLP). It is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As such, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. | ||
[[Image:Detail-146189.jpg|thumb|center|A computer screen displaying a representation of the BERT model|class=only_on_mobile]] | |||
[[Image:Detail-146190.jpg|thumb|center|A computer screen displaying a representation of the BERT model|class=only_on_desktop]] | |||
== Background == | == Background == | ||