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

@inproceedings{Veyseh2019GraphBN,
  title={Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures},
  author={Amir Pouran Ben Veyseh and Thien Huu Nguyen and Dejing Dou},
  booktitle={ACL},
  year={2019}
}
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… Expand
Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks
TLDR
This study proposes a novel gating mechanism to filter noisy information in the hidden vectors of the GCN models for ED based on the information from the trigger candidate and introduces novel mechanisms to achieve the contextual diversity for the gates and the importance score consistency for the graphs and models in ED. Expand
Improving Cross-Lingual Transfer for Event Argument Extraction with Language-Universal Sentence Structures
We study the problem of Cross-lingual Event Argument Extraction (CEAE). The task aims to predict argument roles of entity mentions for events in text, whose language is different from the languageExpand
Factuality Assessment as Modal Dependency Parsing
As the sources of information that we consume everyday rapidly diversify, it is becoming increasingly important to develop NLP tools that help to evaluate the credibility of the information weExpand
An End-to-End Approach for Document-level Event Factuality Identification in Chinese
TLDR
This paper proposes a multi-task framework to join the event detection task and the event factuality identification task, which can interact the two tasks and then provide more accurate event and factuality information. Expand
Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures
TLDR
This work develops a novel deep learning model for document-level ECI (DECI) to accept inter-sentence event mention pairs, and proposes a graph-based model that constructs interaction graphs to capture relevant connections between important objects for DECI in input documents. Expand
Learning to Select Important Context Words for Event Detection
TLDR
A novel method that learns to select relevant context words for ED based on the Gumbel-Softmax trick is proposed, leading to the state-of-the-art performance for ED over different benchmark datasets and settings. Expand
Hierarchical Graph Convolutional Networks for Jointly Resolving Cross-document Coreference of Entity and Event Mentions
TLDR
A novel deep learning model is proposed for CDECR that introduces hierarchical graph convolutional neural networks (GCN) and document-level GCN to jointly resolve entity and event mentions. Expand
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning
TLDR
This work proposes to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the Syntactic connections between the words. Expand
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation
TLDR
A novel graph-based deep learning model that achieves the state-of-the-art performance on three benchmark datasets and proposes a mechanism to obtain the importance scores for each word in the sentences based on the dependency trees that are then injected into the model to improve the representation vectors for ABSA. Expand
He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics
TLDR
Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Expand
...
1
2
...

References

SHOWING 1-10 OF 28 REFERENCES
Graph Convolutional Networks With Argument-Aware Pooling for Event Detection
TLDR
This work investigates a convolutional neural network based on dependency trees to perform event detection and proposes a novel pooling method that relies on entity mentions to aggregate the convolution vectors. Expand
Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets
TLDR
This work proposes an intuitive method for mapping three previously annotated corpora onto a single factuality scale, thereby enabling models to be tested across these corpora and designs a novel model for factuality prediction by first extending a previous rule-based factuality Prediction system and applying it over an abstraction of dependency trees. Expand
One for All: Neural Joint Modeling of Entities and Events
TLDR
This work proposes a novel model to jointly perform predictions for entity mentions, event triggers and arguments based on the shared hidden representations from deep learning, leading to the state-of-the-art performance for event extraction. Expand
Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching
TLDR
A method to transfer the knowledge learned on WSD to ED by matching the neural representations learned for the two tasks is proposed and demonstrated to be effective. Expand
Neural Models of Factuality
TLDR
A substantial expansion of the It Happened portion of the Universal Decompositional Semantics dataset is presented, yielding the largest event factuality dataset to date. Expand
Event Detection and Factuality Assessment with Non-Expert Supervision
TLDR
It is found that non-experts, with very little training, can reliably provide judgments about what events are mentioned and the extent to which the author thinks they actually happened. Expand
Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification
TLDR
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). Expand
Exploring Different Dimensions of Attention for Uncertainty Detection
TLDR
This paper develops attention mechanisms for uncertainty detection by introducing external attention and sequence-preserving attention and develops novel architectures which set the new state of the art on a Wikipedia benchmark dataset and perform similar to the state-of-the-art model on a biomedical benchmark which uses a large set of linguistic features. Expand
Multilingual Modal Sense Classification using a Convolutional Neural Network
TLDR
It is shown that CNNs are superior to manually designed feature-based classifiers and a standard NN classifier, and the feature maps learned by the CNN are analyzed to identify known and previously unattested linguistic features. Expand
FactBank: a corpus annotated with event factuality
TLDR
FactBank is a corpus annotated with information concerning the factuality of events that has been carried out from a descriptive framework of factuality grounded on both theoretical findings and data analysis. Expand
...
1
2
3
...