Editing Question answering (section)

==Architecture==
{{As of|2001}}, question-answering systems typically included a ''question classifier'' module that determined the type of question and the type of answer.<ref>Hirschman, L. & Gaizauskas, R. (2001) [http://journals.cambridge.org/action/displayAbstract?fromPage=online&aid=96167 Natural Language Question Answering. The View from Here]. Natural Language Engineering (2001), 7:4:275-300 Cambridge University Press.</ref>

Different types of question-answering systems employ different architectures. For example, modern open-domain question answering systems may use a retriever-reader architecture. The retriever is aimed at retrieving relevant documents related to a given question, while the reader is used to infer the answer from the retrieved documents. Systems such as [[GPT-3]], T5,<ref>{{Cite arXiv|title=Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer |eprint=1910.10683 |last1=Raffel |first1=Colin |last2=Shazeer |first2=Noam |last3=Roberts |first3=Adam |last4=Lee |first4=Katherine |last5=Narang |first5=Sharan |last6=Matena |first6=Michael |last7=Zhou |first7=Yanqi |last8=Li |first8=Wei |last9=Liu |first9=Peter J. |year=2019 |class=cs.LG }}</ref> and BART<ref>{{Cite arXiv|title=BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension |eprint=1910.13461 |last1=Lewis |first1=Mike |last2=Liu |first2=Yinhan |last3=Goyal |first3=Naman |last4=Ghazvininejad |first4=Marjan |last5=Mohamed |first5=Abdelrahman |last6=Levy |first6=Omer |last7=Stoyanov |first7=Ves |last8=Zettlemoyer |first8=Luke |year=2019 |class=cs.CL }}</ref> use an end-to-end{{jargon inline|date=April 2023}} architecture in which a transformer-based{{jargon inline|date=April 2023}} architecture stores large-scale textual data in the underlying parameters. Such models can answer questions without accessing any external knowledge sources.