TIMERS: Document-level Temporal Relation Extraction

We present TIMERS a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification. Our proposed method leverages rhetorical discourse features and temporal arguments from semantic role labels, in addition to traditional local syntactic features, trained through a Gated RelationalGCN. Extensive experiments show that the proposed model outperforms previous methods by 5-18% on the TDDiscourse, TimeBankDense, and MATRES datasets due to our discourse-level modeling.

[1]  Parminder Bhatia,et al.  Better Document-level Sentiment Analysis from RST Discourse Parsing , 2015, EMNLP.

[2]  Timothy Miller,et al.  A BERT-based Universal Model for Both Within- and Cross-sentence Clinical Temporal Relation Extraction , 2019, Proceedings of the 2nd Clinical Natural Language Processing Workshop.

[3]  Dan Roth,et al.  A Structured Learning Approach to Temporal Relation Extraction , 2017, EMNLP.

[4]  Yusuke Miyao,et al.  Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths , 2017, ACL.

[5]  James Pustejovsky,et al.  TimeML: Robust Specification of Event and Temporal Expressions in Text , 2003, New Directions in Question Answering.

[6]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[7]  Greg Durrett,et al.  Effective Distant Supervision for Temporal Relation Extraction , 2020, ADAPTNLP.

[8]  Benjamin Van Durme,et al.  Fine-Grained Temporal Relation Extraction , 2019, ACL.

[9]  Hyun-Je Song,et al.  WIRE: An Automated Report Generation System using Topical and Temporal Summarization , 2020, SIGIR.

[10]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[11]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

[12]  Arne Neumann.  discoursegraphs: A graph-based merging tool and converter for multilayer annotated corpora , 2015, NODALIDA.

[13]  Carolyn Penstein Rosé,et al.  TDDiscourse: A Dataset for Discourse-Level Temporal Ordering of Events , 2019, SIGdial.

[14]  Marie-Francine Moens,et al.  Temporal Information Extraction by Predicting Relative Time-lines , 2018, EMNLP.

[15]  Jimmy J. Lin,et al.  Simple BERT Models for Relation Extraction and Semantic Role Labeling , 2019, ArXiv.

[16]  Taylor Cassidy,et al.  Dense Event Ordering with a Multi-Pass Architecture , 2014, TACL.

[17]  Nanyun Peng,et al.  Deep Structured Neural Network for Event Temporal Relation Extraction , 2019, CoNLL.

[18]  Olivier Ferret,et al.  Neural Architecture for Temporal Relation Extraction: A Bi-LSTM Approach for Detecting Narrative Containers , 2017, ACL.

[19]  Nanyun Peng,et al.  DEER: A Data Efficient Language Model for Event Temporal Reasoning , 2020, ArXiv.

[20]  Anna Rumshisky,et al.  Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture , 2017, EMNLP.

[21]  Hao Wu,et al.  A Multi-Axis Annotation Scheme for Event Temporal Relations , 2018, ACL.

[22]  Taylor Cassidy,et al.  An Annotation Framework for Dense Event Ordering , 2014, ACL.

[23]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[24]  Nanyun Peng,et al.  TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions , 2020, EMNLP.

[25]  Yizhou Sun,et al.  Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference , 2020, AAAI.

[26]  Tanya Goyal,et al.  Embedding time expressions for deep temporal ordering models , 2019, ACL.

[27]  Yaser Al-Onaizan,et al.  Severing the Edge between before and after: Neural Architectures for Temporal Ordering of Events , 2020, EMNLP.

[28]  Nanyun Peng,et al.  Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction , 2020, EMNLP.

[29]  Mark A. Finlayson,et al.  Distinguishing Between Foreground and Background Events in News , 2020, COLING.

[30]  Marie-Francine Moens,et al.  A Survey on Temporal Reasoning for Temporal Information Extraction from Text , 2019, J. Artif. Intell. Res..

[31]  Jacob Eisenstein,et al.  Representation Learning for Text-level Discourse Parsing , 2014, ACL.

[32]  Nanyun Peng,et al.  Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction , 2019, EMNLP.

[33]  Dan Roth,et al.  An Improved Neural Baseline for Temporal Relation Extraction , 2019, EMNLP.

[34]  Iryna Gurevych,et al.  Temporal Anchoring of Events for the TimeBank Corpus , 2016, ACL.

[35]  Dan Roth,et al.  Joint Constrained Learning for Event-Event Relation Extraction , 2020, EMNLP.

[36]  Christina Lioma,et al.  Rhetorical relations for information retrieval , 2012, SIGIR '12.

[37]  William C. Mann,et al.  RHETORICAL STRUCTURE THEORY: A THEORY OF TEXT ORGANIZATION , 1987 .

[38]  Nanyun Peng,et al.  Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding , 2019, ArXiv.

[39]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[40]  Dan Roth,et al.  CogCompTime: A Tool for Understanding Time in Natural Language , 2018, EMNLP.

[41]  Wang Yubin,et al.  Document-level Relation Extraction with Dual-tier Heterogeneous Graph , 2020, COLING.

[42]  Nanyun Peng,et al.  EventPlus: A Temporal Event Understanding Pipeline , 2021, NAACL.