Exploiting Contextual Information via Dynamic Memory Network for Event Detection

@inproceedings{Liu2018ExploitingCI,
  title={Exploiting Contextual Information via Dynamic Memory Network for Event Detection},
  author={Shaobo Liu and Rui Cheng and Xiaoming Yu and Xueqi Cheng},
  booktitle={EMNLP},
  year={2018}
}
The task of event detection involves identifying and categorizing event triggers. Contextual information has been shown effective on the task. However, existing methods which utilize contextual information only process the context once. We argue that the context can be better exploited by processing the context multiple times, allowing the model to perform complex reasoning and to generate better context representation, thus improving the overall performance. Meanwhile, dynamic memory network… Expand
Context Event Features and Event Embedding Enhanced Event Detection
Extracting valuable information from text has always been a hot point for research and event detection is an essential subtask of information extraction. Most existing methods of event detection onlyExpand
Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection
TLDR
A Dynamic-Memory-Based Prototypical Network (DMB-PN) is proposed, which exploits Dynamic Memory Network (DMN) to not only learn better prototypes for event types, but also produce more robust sentence encodings for event mentions. Expand
Incremental Event Detection via Knowledge Consolidation Networks
TLDR
A Knowledge Consolidation Network (KCN) is proposed, which devise two components, prototype enhanced retrospection and hierarchical distillation, to mitigate the adverse effects of semantic ambiguity and class imbalance, respectively. Expand
Using Mention Segmentation to Improve Event Detection with Multi-head Attention
TLDR
A novel ED method which integrates sentence segmentation into the neural event classification architecture and outperforms the state-of-the-art, where BERT is used as the classification model. Expand
Image Enhanced Event Detection in News Articles
TLDR
This paper proposes a novel Dual Recurrent Multimodal Model, DRMM, to conduct deep interactions between images and sentences for modality features aggregation and superior performance compared to six state-of-art baselines as well as further ablation studies demonstrate the significance of image modality and effectiveness of the proposed architecture. Expand
Improving Event Detection via Open-domain Trigger Knowledge
TLDR
A novel Enrichment Knowledge Distillation (EKD) model to leverage external open-domain trigger knowledge to reduce the in-built biases to frequent trigger words in annotations is proposed. Expand
Implicit Life Event Discovery From Call Transcripts Using Temporal Input Transformation Network
TLDR
A novel deep learning approach based on latent topic modeling and deep recurrent neural networks with memory units to automatically detect implicit events from a customer’s history of call transcripts to detect the implicit life events. Expand
Extracting Events and Their Relations from Texts: A Survey on Recent Research Progress and Challenges
TLDR
This paper summaries some constructed event-centric knowledge graphs and the recent typical approaches for event and event relation extraction, besides task description, widely used evaluation datasets, and challenges, and focuses on three recent important research problems in the event extraction task. Expand
Distilling Discrimination and Generalization Knowledge for Event Detection via Delta-Representation Learning
TLDR
A Delta-learning approach to distill discrimination and generalization knowledge is proposed by effectively decoupling, incrementally learning and adaptively fusing event representation, and achieves state-of-the-art performance on both ACE2005 and KBP2017 datasets. Expand
A Survey of Event Extraction From Text
TLDR
This article provides a comprehensive yet up-to-date survey for event extraction from text, which not only summarizes the task definitions, data sources and performance evaluations, but also provides a taxonomy for its solution approaches. Expand
...
1
2
...

References

SHOWING 1-10 OF 14 REFERENCES
Joint Event Extraction via Recurrent Neural Networks
TLDR
This work proposes to do event extraction in a joint framework with bidirectional recurrent neural networks, thereby benefiting from the advantages of the two models as well as addressing issues inherent in the existing approaches. Expand
Joint Event Extraction via Structured Prediction with Global Features
TLDR
This work proposes a joint framework based on structured prediction which extracts triggers and arguments together so that the local predictions can be mutually improved, and proposes to incorporate global features which explicitly capture the dependencies of multiple triggers and argued. Expand
Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention
TLDR
This model first learns event detection oriented embeddings of documents through a hierarchical and supervised attention based RNN, and uses the learned document embedding to enhance another bidirectional RNN model to identify event triggers and their types in sentences. Expand
Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks
TLDR
A word-representation model to capture meaningful semantic regularities for words and a framework based on a convolutional neural network to capture sentence-level clues are introduced. Expand
Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms
TLDR
This work systematically investigates the proposed model under the supervision of different attention strategies and shows that the approach advances state-of-the-arts and achieves the best F1 score on ACE 2005 dataset. Expand
Relieving the Computational Bottleneck: Joint Inference for Event Extraction with High-Dimensional Features
TLDR
A new model for event extraction is proposed that combines the power of MLNs and SVMs, dwarfing their limitations; the key idea is to reliably learn and process high-dimensional features using SVMs; encode the output of SVMs as low-dimensional, soft formulas in MLNs; and use the superior joint inferencing power ofMLNs to enforce joint consistency constraints over the soft formulas. Expand
Using Document Level Cross-Event Inference to Improve Event Extraction
TLDR
This paper uses document level information from the training corpus to improve the performance of ACE event extraction and uses information about other types of events to make predictions or resolve ambiguities regarding a given event. Expand
Dynamic Memory Networks for Visual and Textual Question Answering
TLDR
The new DMN+ model improves the state of the art on both the Visual Question Answering dataset and the \babi-10k text question-answering dataset without supporting fact supervision. Expand
Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
TLDR
The dynamic memory network (DMN), a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers, is introduced. Expand
Distributed Representations of Sentences and Documents
TLDR
Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models. Expand
...
1
2
...