%0 Conference Proceedings %T DocTime: A Document-level Temporal Dependency Graph Parser %A Mathur, Puneet %A Morariu, Vlad %A Kaynig-Fittkau, Verena %A Gu, Jiuxiang %A Dernoncourt, Franck %A Tran, Quan %A Nenkova, Ani %A Manocha, Dinesh %A Jain, Rajiv %Y Carpuat, Marine %Y de Marneffe, Marie-Catherine %Y Meza Ruiz, Ivan Vladimir %S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies %D 2022 %8 July %I Association for Computational Linguistics %C Seattle, United States %F mathur-etal-2022-doctime %X We introduce DocTime - a novel temporal dependency graph (TDG) parser that takes as input a text document and produces a temporal dependency graph. It outperforms previous BERT-based solutions by a relative 4-8% on three datasets from modeling the problem as a graph network with path-prediction loss to incorporate longer range dependencies. This work also demonstrates how the TDG graph can be used to improve the downstream tasks of temporal questions answering and NLI by a relative 4-10% with a new framework that incorporates the temporal dependency graph into the self-attention layer of Transformer models (Time-transformer). Finally, we develop and evaluate on a new temporal dependency graph dataset for the domain of contractual documents, which has not been previously explored in this setting. %R 10.18653/v1/2022.naacl-main.73 %U https://aclanthology.org/2022.naacl-main.73 %U https://doi.org/10.18653/v1/2022.naacl-main.73 %P 993-1009