Sequence-to-sequence task NLP
noun phrase
Definition: A task that maps an input token sequence to an output token sequence, such as translation or question answering [Google Machine Learning Glossary].
Example in context: “BERT (Bidirectional Encoder Representations from Transformers), a pre-trained Language model, is based on the transformer architecture and is optimized for sequence-to-sequence tasks such as language modeling and machine translation.” [Baswani et al. 2023]
Synonyms: seq2seq
Related terms: encoder-decoder, machine translation