Generative Event Schema Induction with Entity Disambiguation

This paper presents a generative model to event schema induction. Previous methods in the literature only use head words to represent entities. However, elements other than head words contain useful information. For instance, an armed man is more discriminative than man. Our model takes into account this information and precisely represents it using probabilistic topic distributions. We illustrate that such information plays an important role in parameter estimation. Mostly, it makes topic distributions more coherent and more discriminative. Experimental results on benchmark dataset empirically confirm this enhancement.

[1]  Kathleen R. McKeown,et al.  Unsupervised relation learning for event-focused question-answering and domain modelling , 2008 .

[2]  Satoshi Sekine,et al.  Preemptive Information Extraction using Unrestricted Relation Discovery , 2006, NAACL.

[3]  Ronen Feldman,et al.  Clustering for unsupervised relation identification , 2007, CIKM '07.

[4]  Ivan Titov,et al.  Inducing Neural Models of Script Knowledge , 2014, CoNLL.

[5]  Ralph Grishman,et al.  Message Understanding Conference- 6: A Brief History , 1996, COLING.

[6]  Yifan He,et al.  An Information Extraction Customizer , 2014, TSD.

[7]  Siddharth Patwardhan,et al.  A Unified Model of Phrasal and Sentential Evidence for Information Extraction , 2009, EMNLP.

[8]  Vasileios Hatzivassiloglou,et al.  Automatic Creation of Domain Templates , 2006, ACL.

[9]  Satoshi Sekine,et al.  On-Demand Information Extraction , 2006, ACL.

[10]  Sanda M. Harabagiu,et al.  Incremental Topic Representations , 2004, COLING.

[11]  Robin Collier,et al.  Automatic template creation for information extraction , 1998 .

[12]  Siddharth Patwardhan,et al.  Effective Information Extraction with Semantic Affinity Patterns and Relevant Regions , 2007, EMNLP.

[13]  Ralph Grishman,et al.  Ensemble Semantics for Large-scale Unsupervised Relation Extraction , 2012, EMNLP.

[14]  Romaric Besançon,et al.  Text Segmentation and Graph-based Method for Template Filling in Information Extraction , 2011, IJCNLP.

[15]  Nathanael Chambers,et al.  Template-Based Information Extraction without the Templates , 2011, ACL.

[16]  Cosmin Adrian Bejan.  Unsupervised Discovery of Event Scenarios from Texts , 2008, FLAIRS Conference.

[17]  Roger C. Schank,et al.  Language and Memory , 1986, Cogn. Sci..

[18]  Ivan Titov,et al.  A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge , 2014, EACL.

[19]  Manfred Pinkal,et al.  Learning Script Knowledge with Web Experiments , 2010, ACL.

[20]  Tat-Seng Chua,et al.  Modeling Context in Scenario Template Creation , 2008, IJCNLP.

[21]  Ralph Grishman,et al.  Discovering Relations among Named Entities from Large Corpora , 2004, ACL.

[22]  Nathanael Chambers,et al.  Unsupervised Learning of Narrative Schemas and their Participants , 2009, ACL.

[23]  Gerald DeJong,et al.  An Overview of the FRUMP System Introduction , 2014 .

[24]  Jackie Chi Kit Cheung,et al.  Probabilistic Frame Induction , 2013, NAACL.

[25]  Beth Sundheim.  Third Message Understanding Evaluation and Conference (MUC-3): Phase 1 Status Report , 1991, HLT.

[26]  Günter Neumann,et al.  Unsupervised Relation Extraction From Web Documents , 2008, LREC.

[27]  Nathanael Chambers,et al.  Event Schema Induction with a Probabilistic Entity-Driven Model , 2013, EMNLP.

[28]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[29]  Raymond J. Mooney,et al.  Statistical Script Learning with Multi-Argument Events , 2014, EACL.

[30]  Ryan Gabbard,et al.  Extreme Extraction – Machine Reading in a Week , 2011, EMNLP.

[31]  Brigitte Grau,et al.  An Aggregation Procedure for Building Episodic Memory , 1997, IJCAI.

[32]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[33]  Nathanael Chambers,et al.  Unsupervised Learning of Narrative Event Chains , 2008, ACL.

[34]  Oren Etzioni,et al.  Generating Coherent Event Schemas at Scale , 2013, EMNLP.