Comparar métodos

	Resposta a Perguntas (QA)	Tradução automática
Área	Mineração de texto	Mineração de texto
Família	Process / pipeline	Process / pipeline
Ano de origem	—	—
Autor original	—	—
Tipo	NLP text-comprehension task	NLP text-to-text generation task
Fonte seminal	Rajpurkar, P. et al. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. EMNLP.	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. International Conference on Learning Representations (ICLR).
Outros nomes	QA, machine reading comprehension, Soru Cevaplama (Question Answering)	MT, neural machine translation, automatic translation, Makine Çevirisi (Machine Translation)
Relacionados	4	3
Resumo	Question answering is a natural-language-processing task that automatically answers natural-language questions grounded in a given context passage, using either extractive or generative approaches. The task was crystallised by the SQuAD benchmark of Rajpurkar et al. (2016), and later models such as XLNet (Yang et al., 2019) pushed reading-comprehension accuracy higher.	Machine translation (MT) is a natural-language-processing task that automatically converts text in one language into another. Modern MT is built on neural sequence-to-sequence models — the attention mechanism introduced by Bahdanau et al. (2015) and the transformer architecture of Vaswani et al. (2017) — and it widens access to sources for multilingual data analysis and research.