Learning Constraints for Consistent Timeline Extraction

We present a distantly supervised system for extracting the temporal bounds of fluents (relations which only hold during certain times, such as attends school). Unlike previous pipelined approaches, our model does not assume independence between each fluent or even between named entities with known connections (parent, spouse, employer, etc.). Instead, we model what makes timelines of fluents consistent by learning cross-fluent constraints, potentially spanning entities as well. For example, our model learns that someone is unlikely to start a job at age two or to marry someone who hasn't been born yet. Our system achieves a 36% error reduction over a pipelined baseline.

[1]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[2]  Angel X. Chang,et al.  SUTime: A library for recognizing and normalizing time expressions , 2012, LREC.

[3]  Valentin I. Spitkovsky,et al.  Stanford's Distantly-Supervised Slot-Filling System , 2011, TAC.

[4]  Heng Ji,et al.  CUNY BLENDER TAC-KBP2011 Temporal Slot Filling System Description , 2011, TAC.

[5]  Heeyoung Lee,et al.  Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task , 2011, CoNLL Shared Task.

[6]  Daniel Jurafsky,et al.  Distant supervision for relation extraction without labeled data , 2009, ACL.

[7]  Heng Ji,et al.  Overview of the TAC 2010 Knowledge Base Population Track , 2010 .

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

[9]  Mark Craven,et al.  Constructing Biological Knowledge Bases by Extracting Information from Text Sources , 1999, ISMB.

[10]  Yuji Matsumoto,et al.  Jointly Identifying Temporal Relations with Markov Logic , 2009, ACL.

[11]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[12]  Tom M. Mitchell,et al.  Coupled temporal scoping of relational facts , 2012, WSDM '12.

[13]  Christopher D. Manning,et al.  Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling , 2005, ACL.

[14]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.

[15]  John Dunnion,et al.  UCD IIRG at TAC 2012 , 2012, TAC.

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

[17]  Daniel S. Weld,et al.  Temporal Information Extraction , 2010, AAAI.

[18]  Gerhard Weikum,et al.  Harvesting facts from textual web sources by constrained label propagation , 2011, CIKM '11.

[19]  Alexander M. Rush,et al.  Dual Decomposition for Parsing with Non-Projective Head Automata , 2010, EMNLP.

[20]  Anselmo Peñas,et al.  A distant supervised learning system for the TAC-KBP Slot Filling and Temporal Slot Filling Tasks , 2011, TAC.

[21]  Andrew McCallum,et al.  Fast and Robust Joint Models for Biomedical Event Extraction , 2011, EMNLP.

[22]  Christopher D. Manning,et al.  The Stanford Typed Dependencies Representation , 2008, CF+CDPE@COLING.

[23]  Ming-Wei Chang,et al.  Discriminative Learning over Constrained Latent Representations , 2010, NAACL.

[24]  Christopher D. Manning,et al.  A Global Joint Model for Semantic Role Labeling , 2008, CL.

[25]  Leon Derczynski,et al.  USFD at KBP 2011: Entity Linking, Slot Filling and Temporal Bounding , 2011, TAC.

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

[27]  Eric P. Xing,et al.  Concise Integer Linear Programming Formulations for Dependency Parsing , 2009, ACL.

[28]  Ido Dagan,et al.  Global Learning of Typed Entailment Rules , 2011, ACL.