Determining Event Durations: Models and Error Analysis

This paper presents models to predict event durations. We introduce aspectual features that capture deeper linguistic information than previous work, and experiment with neural networks. Our analysis shows that tense, aspect and temporal structure of the clause provide useful clues, and that an LSTM ensemble captures relevant context around the event.

[1]  Jerry R. Hobbs,et al.  Annotating and Learning Event Durations in Text , 2011, Computational Linguistics.

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

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

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Percy Liang,et al.  Semi-Supervised Learning for Natural Language , 2005 .

[6]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[7]  James Pustejovsky,et al.  ISO-TimeML: An International Standard for Semantic Annotation , 2010, LREC.

[8]  Treebank Penn,et al.  Linguistic Data Consortium , 1999 .

[9]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[10]  Manfred Pinkal,et al.  Situation entity types: automatic classification of clause-level aspect , 2016, ACL.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Jennifer Williams,et al.  Extracting and modeling durations for habits and events from Twitter , 2012, ACL.

[13]  Nathanael Chambers,et al.  Using Query Patterns to Learn the Duration of Events , 2011, IWCS.

[14]  Zeno Vendler,et al.  Verbs and Times , 1957, The Language of Time - A Reader.

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

[16]  Yoshua Bengio,et al.  Word Representations: A Simple and General Method for Semi-Supervised Learning , 2010, ACL.