TY - GEN
T1 - Extracting action sequences from texts based on deep reinforcement learning
AU - Feng, Wenfeng
AU - Zhuo, Hankz Hankui
AU - Kambhampati, Subbarao
N1 - Funding Information:
Zhuo thanks the National Key Research and Development Program of China (2016YFB0201900), National Natural Science Foundation of China (U1611262), Guangdong Natural Science Funds for Distinguished Young Scholar (2017A030306028), Pearl River Science and Technology New Star of Guangzhou, and Guangdong Province Key Laboratory of Big Data Analysis and Processing for the support of this research. Kambhampati’s research is supported in part by the AFOSR grant FA9550-18-1-0067, ONR grants N00014161-2892, N00014-13-1-0176, N00014-13-1-0519, N00014-15-1-2027, and the NASA grant NNX17AD06G.
Publisher Copyright:
© 2018 International Joint Conferences on Artificial Intelligence. All right reserved.
PY - 2018
Y1 - 2018
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
U2 - 10.24963/ijcai.2018/565
DO - 10.24963/ijcai.2018/565
M3 - Conference contribution
AN - SCOPUS:85055708204
T3 - IJCAI International Joint Conference on Artificial Intelligence
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
T2 - 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
Y2 - 13 July 2018 through 19 July 2018
ER -