Content deleted Content added
ce |
Citation bot (talk | contribs) Add: date. | Use this bot. Report bugs. | Suggested by Headbomb | #UCB_toolbar |
||
Line 6:
== Commercial products ==
In 2022 [[Google Docs]] released an automatic summarization feature.<ref>{{Cite web |title=Auto-generated Summaries in Google Docs |url=http://ai.googleblog.com/2022/03/auto-generated-summaries-in-google-docs.html |access-date=2022-04-03 |website=Google AI Blog |date=23 March 2022 |language=en}}</ref>
==Approaches==
Line 167:
===Recent approaches===
Recently the rise of [[Transformer (machine learning model)|transformer models]] replacing more traditional [[Rnn (software)|RNN]] ([[LSTM]]) have provided a flexibility in the mapping of text sequences to text sequences of a different type, which is well suited to automatic summarization. This includes models such as T5<ref>{{Cite web |title=Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer |url=http://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html |access-date=2022-04-03 |website=Google AI Blog |date=24 February 2020 |language=en}}</ref> and Pegasus.<ref>Zhang, J., Zhao, Y., Saleh, M., & Liu, P. (2020, November). Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In International Conference on Machine Learning (pp. 11328-11339). PMLR.</ref>
==See also==
| |||