Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification

Event factuality identification is an important semantic task in NLP. Traditional research heavily relies on annotated texts. This paper proposes a twostep framework, first extracting essential factors related with event factuality from raw texts as the input, and then identifying the factuality of events via a Generative Adversarial Network with Auxiliary Classification (AC-GAN). The use of AC-GAN allows the model to learn more syntactic information and address the imbalance among factuality values. Experimental results on FactBank show that our method significantly outperforms several stateof-the-art baselines, particularly on events with embedded sources, speculative and negative factuality values.

[1]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[2]  Mirella Lapata,et al.  Neural Semantic Role Labeling with Dependency Path Embeddings , 2016, ACL.

[3]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[4]  Zoubin Ghahramani,et al.  Proceedings of the 24th international conference on Machine learning , 2007, ICML 2007.

[5]  Eric Gilbert,et al.  Modeling Factuality Judgments in Social Media Text , 2014, ACL.

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

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

[8]  Barbara Plank,et al.  Proceedings of ACL 2016 , 2016 .

[9]  Xin Lin,et al.  Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN , 2017, 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR).

[10]  Nate Chambers.  NavyTime: Event and Time Ordering from Raw Text , 2013, SemEval@NAACL-HLT.

[11]  M. V. Rossum,et al.  In Neural Computation , 2022 .

[12]  Stephan Oepen,et al.  Speculation and Negation: Rules, Rankers, and the Role of Syntax , 2012, CL.

[13]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

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

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

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

[17]  Jason Weston,et al.  Proceedings of the 1st Workshop on Representation Learning for NLP , 2016 .

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

[19]  James Pustejovsky,et al.  TimeML: Robust Specification of Event and Temporal Expressions in Text , 2003, New Directions in Question Answering.

[20]  Zhiyuan Liu,et al.  Neural Sentiment Classification with User and Product Attention , 2016, EMNLP.

[21]  Biswarup Bhattacharya,et al.  Handwriting Profiling Using Generative Adversarial Networks , 2016, AAAI.

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

[23]  Yorick Wilks,et al.  A New Dataset and Evaluation for Belief/Factuality , 2015, *SEMEVAL.