TY - GEN
T1 - Incorporating Task-Specific Concept Knowledge into Script Learning
AU - Sun, Chenkai
AU - Xu, Tie
AU - Zhai, Cheng Xiang
AU - Ji, Heng
N1 - We would like to thank the anonymous reviewers for their constructive suggestions on our work and thank the raters for their help on manual evaluation. This research is based upon work supported in part by U.S. DARPA KAIROS Program No. FA8750-19-2-1004. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the of ficial policies, either expressed or implied, of DARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
PY - 2023
Y1 - 2023
N2 - In this paper, we present TETRIS, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.
AB - In this paper, we present TETRIS, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance.
UR - http://www.scopus.com/inward/record.url?scp=85159861790&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85159861790&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85159861790
T3 - EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
SP - 3018
EP - 3032
BT - EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023
Y2 - 2 May 2023 through 6 May 2023
ER -