Extracting action sequences from texts based on deep reinforcement learning

Wenfeng Feng, Hankz Hankui Zhuo, Subbarao Kambhampati

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Extracting action sequences from texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require either the set of candidate actions be provided in advance, or action descriptions are restricted to a specific form, e.g., description templates. In this paper we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view "selecting" or "eliminating" words from texts as "actions", and texts associated with actions as "states". We build Q-networks to learn policies of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches.

Original languageEnglish (US)
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJerome Lang
PublisherInternational Joint Conferences on Artificial Intelligence
Pages4064-4070
Number of pages7
Volume2018-July
ISBN (Electronic)9780999241127
StatePublished - Jan 1 2018
Event27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden
Duration: Jul 13 2018Jul 19 2018

Other

Other27th International Joint Conference on Artificial Intelligence, IJCAI 2018
CountrySweden
CityStockholm
Period7/13/187/19/18

Fingerprint

Reinforcement learning
Navigation

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Feng, W., Zhuo, H. H., & Kambhampati, S. (2018). Extracting action sequences from texts based on deep reinforcement learning. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (Vol. 2018-July, pp. 4064-4070). International Joint Conferences on Artificial Intelligence.

Extracting action sequences from texts based on deep reinforcement learning. / Feng, Wenfeng; Zhuo, Hankz Hankui; Kambhampati, Subbarao.

Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. ed. / Jerome Lang. Vol. 2018-July International Joint Conferences on Artificial Intelligence, 2018. p. 4064-4070.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Feng, W, Zhuo, HH & Kambhampati, S 2018, Extracting action sequences from texts based on deep reinforcement learning. in J Lang (ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. vol. 2018-July, International Joint Conferences on Artificial Intelligence, pp. 4064-4070, 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, 7/13/18.
Feng W, Zhuo HH, Kambhampati S. Extracting action sequences from texts based on deep reinforcement learning. In Lang J, editor, Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. Vol. 2018-July. International Joint Conferences on Artificial Intelligence. 2018. p. 4064-4070
Feng, Wenfeng ; Zhuo, Hankz Hankui ; Kambhampati, Subbarao. / Extracting action sequences from texts based on deep reinforcement learning. Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. editor / Jerome Lang. Vol. 2018-July International Joint Conferences on Artificial Intelligence, 2018. pp. 4064-4070
@inproceedings{9a4202f7eea142648c7673045d078d8a,
title = "Extracting action sequences from texts based on deep reinforcement learning",
abstract = "Extracting action sequences from texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require either the set of candidate actions be provided in advance, or action descriptions are restricted to a specific form, e.g., description templates. In this paper we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view {"}selecting{"} or {"}eliminating{"} words from texts as {"}actions{"}, and texts associated with actions as {"}states{"}. We build Q-networks to learn policies of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches.",
author = "Wenfeng Feng and Zhuo, {Hankz Hankui} and Subbarao Kambhampati",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2018-July",
pages = "4064--4070",
editor = "Jerome Lang",
booktitle = "Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018",
publisher = "International Joint Conferences on Artificial Intelligence",

}

TY - GEN

T1 - Extracting action sequences from texts based on deep reinforcement learning

AU - Feng, Wenfeng

AU - Zhuo, Hankz Hankui

AU - Kambhampati, Subbarao

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Extracting action sequences from texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require either the set of candidate actions be provided in advance, or action descriptions are restricted to a specific form, e.g., description templates. In this paper we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view "selecting" or "eliminating" words from texts as "actions", and texts associated with actions as "states". We build Q-networks to learn policies of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches.

AB - Extracting action sequences from texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require either the set of candidate actions be provided in advance, or action descriptions are restricted to a specific form, e.g., description templates. In this paper we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view "selecting" or "eliminating" words from texts as "actions", and texts associated with actions as "states". We build Q-networks to learn policies of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches.

UR - http://www.scopus.com/inward/record.url?scp=85055708204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055708204&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2018-July

SP - 4064

EP - 4070

BT - Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018

A2 - Lang, Jerome

PB - International Joint Conferences on Artificial Intelligence

ER -