Liberal Event Extraction and Event Schema Induction

We propose a brand new “Liberal” Event Extraction paradigm to extract events and discover event schemas from any input corpus simultaneously. We incorporate symbolic (e.g., Abstract Meaning Representation) and distributional semantics to detect and represent event structures and adopt a joint typing framework to simultaneously extract event types and argument roles and discover an event schema. Experiments on general and specific domains demonstrate that this framework can construct high-quality schemas with many event and argument role types, covering a high proportion of event types and argument roles in manually defined schemas. We show that extraction performance using discovered schemas is comparable to supervised models trained from a large amount of data labeled according to predefined event types. The extraction quality of new event types is also promising.

[1]  Joakim Nivre,et al.  Natural Language Parsing , 2006 .

[2]  Heng Ji,et al.  Knowledge Base Population: Successful Approaches and Challenges , 2011, ACL.

[3]  Daniel Marcu,et al.  Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text , 2015, AAAI.

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

[5]  Oren Etzioni,et al.  The Tradeoffs Between Open and Traditional Relation Extraction , 2008, ACL.

[6]  Yizhou Sun,et al.  Semantic Frame-Based Document Representation for Comparable Corpora , 2013, 2013 IEEE 13th International Conference on Data Mining.

[7]  Hiroaki Sato,et al.  The FrameNet Data and Software , 2003, ACL.

[8]  Marianna Apidianaki,et al.  Latent Semantic Word Sense Induction and Disambiguation , 2011, ACL.

[9]  Paolo Rosso,et al.  UPV-SI: Word Sense Induction using Self Term Expansion , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

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

[11]  Zhiyuan Liu,et al.  Phrase Type Sensitive Tensor Indexing Model for Semantic Composition , 2015, AAAI.

[12]  Mirella Lapata,et al.  Bayesian Word Sense Induction , 2009, EACL.

[13]  Jing Wang,et al.  A Sense-Topic Model for Word Sense Induction with Unsupervised Data Enrichment , 2015, TACL.

[14]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[15]  Romaric Besançon,et al.  Generative Event Schema Induction with Entity Disambiguation , 2015, ACL.

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

[17]  Suresh Manandhar,et al.  SemEval-2010 Task 14: Word Sense Induction &Disambiguation , 2010, SemEval@ACL.

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

[19]  Chuan Wang,et al.  Boosting Transition-based AMR Parsing with Refined Actions and Auxiliary Analyzers , 2015, ACL.

[20]  Andrew McCallum,et al.  Universal schema for entity type prediction , 2013, AKBC '13.

[21]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[22]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition , 2003, CoNLL.

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

[24]  Mitchell P. Marcus,et al.  OntoNotes: The 90% Solution , 2006, NAACL.

[25]  Stefan Bordag.  Word Sense Induction: Triplet-Based Clustering and Automatic Evaluation , 2006, EACL.

[26]  Heng Ji,et al.  Refining Event Extraction through Cross-Document Inference , 2008, ACL.

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

[28]  Roberto Navigli,et al.  Word sense disambiguation: A survey , 2009, CSUR.

[29]  Heng Ji,et al.  Joint Event Extraction via Structured Prediction with Global Features , 2013, ACL.

[30]  Christopher Potts,et al.  Recursive Neural Networks for Learning Logical Semantics , 2014, ArXiv.

[31]  Jun Zhao,et al.  Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks , 2015, ACL.

[32]  David R. Dowty,et al.  Natural Language Parsing , 2005 .

[33]  Chen Chen,et al.  Joint Modeling for Chinese Event Extraction with Rich Linguistic Features , 2012, COLING.

[34]  Jun'ichi Tsujii,et al.  A Rich Feature Vector for Protein-Protein Interaction Extraction from Multiple Corpora , 2009, EMNLP.

[35]  Ralph Grishman,et al.  Event Detection and Domain Adaptation with Convolutional Neural Networks , 2015, ACL.

[36]  Oren Etzioni,et al.  Open Information Extraction: The Second Generation , 2011, IJCAI.

[37]  Andrew McCallum,et al.  Probabilistic Databases of Universal Schema , 2012, AKBC-WEKEX@NAACL-HLT.

[38]  Jeffrey Pennington,et al.  Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions , 2011, EMNLP.

[39]  Bin Ma,et al.  Using Cross-Entity Inference to Improve Event Extraction , 2011, ACL.

[40]  Oren Etzioni,et al.  Open domain event extraction from twitter , 2012, KDD.

[41]  Mihai Surdeanu,et al.  Event Extraction as Dependency Parsing , 2011, ACL.

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

[43]  Phil Blunsom,et al.  The Role of Syntax in Vector Space Models of Compositional Semantics , 2013, ACL.

[44]  Mirella Lapata,et al.  An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  Hwee Tou Ng,et al.  It Makes Sense: A Wide-Coverage Word Sense Disambiguation System for Free Text , 2010, ACL.

[46]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[47]  Michael Gamon,et al.  Mining Entity Types from Query Logs via User Intent Modeling , 2012, ACL.

[48]  Neville Ryant,et al.  A Large-scale Classication of English Verbs , 2006 .

[49]  Doug Downey,et al.  Unsupervised named-entity extraction from the Web: An experimental study , 2005, Artif. Intell..

[50]  Ralph Grishman,et al.  Using Document Level Cross-Event Inference to Improve Event Extraction , 2010, ACL.

[51]  Lynn Carlson,et al.  Tasks, Domains, and Languages for Information Extraction , 1993, TIPSTER.

[52]  Noah A. Smith,et al.  Frame-Semantic Parsing , 2014, CL.

[53]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[54]  Quoc V. Le,et al.  Grounded Compositional Semantics for Finding and Describing Images with Sentences , 2014, TACL.

[55]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[56]  Nianwen Xue,et al.  CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes , 2011, CoNLL Shared Task.

[57]  Christopher D. Manning,et al.  Generating Typed Dependency Parses from Phrase Structure Parses , 2006, LREC.

[58]  Guodong Zhou,et al.  Dependency-Driven Feature-based Learning for Extracting Protein-Protein Interactions from Biomedical Text , 2010, COLING.

[59]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[60]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.