Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource

Extracting temporal relations (before, after, overlapping, etc.) is a key aspect of understanding events described in natural language. We argue that this task would gain from the availability of a resource that provides prior knowledge in the form of the temporal order that events usually follow. This paper develops such a resource -- a probabilistic knowledge base acquired in the news domain -- by extracting temporal relations between events from the New York Times (NYT) articles over a 20-year span (1987--2007). We show that existing temporal extraction systems can be improved via this resource. As a byproduct, we also show that interesting statistics can be retrieved from this resource, which can potentially benefit other time-aware tasks. The proposed system and resource are both publicly available.

[1]  Tommaso Caselli,et al.  SemEval-2010 Task 13: TempEval-2 , 2010, *SEMEVAL.

[2]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[3]  James Pustejovsky,et al.  Machine Learning of Temporal Relations , 2006, ACL.

[4]  James Pustejovsky,et al.  SemEval-2017 Task 12: Clinical TempEval , 2017, *SEMEVAL.

[5]  Pascal Denis,et al.  Predicting Globally-Coherent Temporal Structures from Texts via Endpoint Inference and Graph Decomposition , 2011, IJCAI.

[6]  Eneko Agirre,et al.  SemEval-2015 Task 4: TimeLine: Cross-Document Event Ordering , 2015, *SEMEVAL.

[7]  James Pustejovsky,et al.  Temporal Processing with the TARSQI Toolkit , 2008, COLING.

[8]  Dan Roth,et al.  Minimally Supervised Event Causality Identification , 2011, EMNLP.

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

[10]  Patrick Pantel,et al.  VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations , 2004, EMNLP.

[11]  James Pustejovsky,et al.  SemEval-2013 Task 1: TempEval-3: Evaluating Time Expressions, Events, and Temporal Relations , 2013, *SEMEVAL.

[12]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[13]  James Pustejovsky,et al.  SemEval-2015 Task 6: Clinical TempEval , 2015, *SEMEVAL.

[14]  Teruko Mitamura,et al.  Event Detection Using Frame-Semantic Parser , 2017, NEWS@ACL.

[15]  Yoav Freund,et al.  Large Margin Classification Using the Perceptron Algorithm , 1998, COLT.

[16]  Dan Roth,et al.  Event Detection and Co-reference with Minimal Supervision , 2016, EMNLP.

[17]  Nathanael Chambers,et al.  Jointly Combining Implicit Constraints Improves Temporal Ordering , 2008, EMNLP.

[18]  James F. Allen,et al.  Temporal Evaluation , 2011, ACL.

[19]  Dan Roth,et al.  Two Discourse Driven Language Models for Semantics , 2016, ACL.

[20]  Dan Roth,et al.  An NLP Curator (or: How I Learned to Stop Worrying and Love NLP Pipelines) , 2012, LREC.

[21]  M. Felisa Verdejo,et al.  Events are Not Simple: Identity, Non-Identity, and Quasi-Identity , 2013, EVENTS@NAACL-HLT.

[22]  Shan Wang,et al.  Classifying Temporal Relations Between Events , 2007, ACL.

[23]  Zhifang Sui,et al.  Towards Time-Aware Knowledge Graph Completion , 2016, COLING.

[24]  Yukari Yamakawa,et al.  Event Nugget Annotation: Processes and Issues , 2015, EVENTS@HLP-NAACL.

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

[26]  James Pustejovsky,et al.  SemEval-2007 Task 15: TempEval Temporal Relation Identification , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[27]  Seth Kulick,et al.  From Light to Rich ERE: Annotation of Entities, Relations, and Events , 2015, EVENTS@HLP-NAACL.

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

[29]  Regina Barzilay,et al.  Inducing Temporal Graphs , 2006, EMNLP.

[30]  Dan Roth,et al.  Learning Based Java for Rapid Development of NLP Systems , 2010, LREC.

[31]  James Pustejovsky,et al.  SemEval-2015 Task 5: QA TempEval - Evaluating Temporal Information Understanding with Question Answering , 2015, *SEMEVAL.

[32]  Dan Roth,et al.  A Linear Programming Formulation for Global Inference in Natural Language Tasks , 2004, CoNLL.

[33]  James H. Martin,et al.  Timelines from Text: Identification of Syntactic Temporal Relations , 2007, International Conference on Semantic Computing (ICSC 2007).

[34]  Dan Roth,et al.  Joint Inference for Event Timeline Construction , 2012, EMNLP.

[35]  Paramita Mirza,et al.  CATENA: CAusal and TEmporal relation extraction from NAtural language texts , 2016, COLING.

[36]  Gerhard Weikum,et al.  YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia: Extended Abstract , 2013, IJCAI.