Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures

Event factuality prediction (EFP) is the task of assessing the degree to which an event mentioned in a sentence has happened. For this task, both syntactic and semantic information are crucial to identify the important context words. The previous work for EFP has only combined these information in a simple way that cannot fully exploit their coordination. In this work, we introduce a novel graph-based neural network for EFP that can integrate the semantic and syntactic information more effectively. Our experiments demonstrate the advantage of the proposed model for EFP.

[1]  Anette Frank,et al.  Multilingual Modal Sense Classification using a Convolutional Neural Network , 2016, Rep4NLP@ACL.

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

[3]  James Pustejovsky,et al.  A factuality profiler for eventualities in text , 2008 .

[4]  Heike Adel,et al.  Exploring Different Dimensions of Attention for Uncertainty Detection , 2016, EACL.

[5]  Ralph Grishman,et al.  Joint Event Extraction via Recurrent Neural Networks , 2016, NAACL.

[6]  James Pustejovsky,et al.  FactBank: a corpus annotated with event factuality , 2009, Lang. Resour. Evaluation.

[7]  Peifeng Li,et al.  A two-step approach for event factuality identification , 2015, 2015 International Conference on Asian Language Processing (IALP).

[8]  Ralph Grishman,et al.  Graph Convolutional Networks With Argument-Aware Pooling for Event Detection , 2018, AAAI.

[9]  Rachel Rudinger,et al.  Neural Models of Factuality , 2018, NAACL.

[10]  Ralph Grishman,et al.  A Two-stage Approach for Extending Event Detection to New Types via Neural Networks , 2016, Rep4NLP@ACL.

[11]  James Pustejovsky,et al.  Are You Sure That This Happened? Assessing the Factuality Degree of Events in Text , 2012, CL.

[12]  Ralph Grishman,et al.  New York University 2016 System for KBP Event Nugget: A Deep Learning Approach , 2016, TAC.

[13]  Thien Huu Nguyen,et al.  Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching , 2018, EMNLP.

[14]  C. Condoravdi,et al.  Computing relative polarity for textual inference , 2006 .

[15]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[16]  Chantal van Son,et al.  MEANTIME, the NewsReader Multilingual Event and Time Corpus , 2016, LREC.

[17]  Christopher Potts,et al.  Did It Happen? The Pragmatic Complexity of Veridicality Assessment , 2012, CL.

[18]  Weiwei Guo,et al.  Committed Belief Annotation and Tagging , 2009, Linguistic Annotation Workshop.

[19]  Teruko Mitamura,et al.  Overview of TAC KBP 2015 Event Nugget Track , 2015, TAC.

[20]  Yue Zhang,et al.  Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification , 2018, IJCAI.

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

[22]  Ido Dagan,et al.  TruthTeller: Annotating Predicate Truth , 2013, NAACL.

[23]  Avirup Sil,et al.  Toward Mention Detection Robustness with Recurrent Neural Networks , 2016, ArXiv.

[24]  Yejin Choi,et al.  Event Detection and Factuality Assessment with Non-Expert Supervision , 2015, EMNLP.

[25]  Owen Rambow,et al.  Automatic Committed Belief Tagging , 2010, COLING.

[26]  Ido Dagan,et al.  Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets , 2017, ACL.

[27]  Thien Huu Nguyen,et al.  One for All: Neural Joint Modeling of Entities and Events , 2018, AAAI.