Fetching the paper…

Reading the bibliography…

2021

GPT3-to-plan: Extracting plans from text using GPT-3

Olmo, Alberto, Sreedharan, Sarath, Kambhampati, Subbarao

Original
PDF
Post on X

Understand

Operations in many essential industries including finance and banking are often characterized by the need to perform repetitive sequential tasks.

Despite their criticality to the business, workflows are rarely fully automated or even formally specified, though there may exist a number of natural language documents describing these procedures for the employees of the company.
Plan extraction methods provide us with the possibility of extracting structure plans from such natural language descriptions of the plans/workflows, which could then be leveraged by an automated system.
In this paper, we investigate the utility of generalized language models in performing such extractions directly from such texts.

GPT3-to-plan: Extracting plans from text using GPT-3 · Around

Built on

Reinforcement Learning for Mapping Instructions to Actions
Branavan, S.; Chen, H.; Zettlemoyer, L.; and Barzilay, R. 2009 · 2009
Earlier work this paper cites.
From unstructured web knowledge to plan descriptions
Addis, A.; and Borrajo, D. 2010 · 2010
Earlier work this paper cites.
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Ma, X.; and Hovy, E. H. 2016 · 2016
Earlier work this paper cites.
Listen, attend, and walk: Neural mapping of navigational instructions to action sequences
Mei, H.; Bansal, M.; and Walter, M. 2016 · 2016
Earlier work this paper cites.

Similar

Navigational instruction generation as inverse reinforcement learning with neural machine translation
Daniele, A. F.; Bansal, M.; and Walter, M. R. 2017 · 2017
Cited alongside, same era.
Framer: Planning models from natural language action descriptions
Lindsay, A.; Read, J.; Ferreira, J.; Hayton, T.; Porteous, J.; and Gregory, P. 2017 · 2017
Cited alongside, same era.
Extracting action sequences from texts based on deep reinforcement learning
Original
Feng, W.; Zhuo, H. H.; and Kambhampati, S. 2018 · 2018
Cited alongside, same era.
OpenWebText Corpus
Gokaslan, A.; and Cohen, V. 2019 · 2019
Cited alongside, same era.

Then

Language models are unsupervised multitask learners
Original
Radford, A.; Wu, J.; Child, R.; Luan, D.; Amodei, D.; and Sutskever, I. 2019 · 2019
Later among the works it cites.
Language Models are Few-Shot Learners
Brown, T.; Mann, B.; and et al., R. 2020 · 2020
Later among the works it cites.
NLtoPDDL: One-Shot Learning of PDDL Models from Natural Language Process Manuals
Miglani, S.; and Yorke-Smith, N. 2020 · 2020
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…