scholarly journals A Neural Model for Joint Event Detection and Summarization

2017 ◽  
Author(s):  
Zhongqing Wang ◽  
Yue Zhang
Keyword(s):  
Event Detection ◽  
Neural Model ◽  
Representation Learning ◽  
Joint Model ◽  
Large Group ◽  
Joint Event

Twitter new event detection aims to identify first stories in a tweet stream. Typical approaches consider two sub tasks. First, it is necessary to filter out mundane or irrelevant tweets. Second, tweets are grouped automatically into event clusters. Traditionally, these two sub tasks are processed separately, and integrated under a pipeline setting, despite that there is inter-dependence between the two tasks. In addition, one further related task is summarization, which is to extract a succinct summary for representing a large group of tweets. Summarization is related to detection, under the new event setting in that salient information is universal between event representing tweets and informative event summaries. In this paper, we build a joint model to filter, cluster, and summarize the tweets for new events. In particular, deep representation learning is used to vectorize tweets, which serves as basis that connects tasks. A neural stacking model is used for integrating a pipeline of different sub tasks, and for better sharing between the predecessor and successors. Experiments show that our proposed neural joint model is more effective compared to its pipeline baseline.

A neural model for joint event detection and prediction

2020 ◽  
Vol 407 ◽  
pp. 376-384
Author(s):  
Linmei Hu ◽  
Shuqi Yu ◽  
Bin Wu ◽  
Chao Shao ◽  
Xiaoli Li
Keyword(s):  
Event Detection ◽  
Neural Model ◽  
Joint Event

scholarly journals Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model

2019 ◽  
Author(s):  
Junchi Zhang ◽  
Yanxia Qin ◽  
Yue Zhang ◽  
Mengchi Liu ◽  
Donghong Ji
Keyword(s):  
State Transition ◽  
Transition Process ◽  
Neural Model ◽  
Joint Model ◽  
Event Extraction ◽  
Traditional Methods ◽  
Single Task ◽  
Output Structure ◽  
Complex Joint ◽  
Argument Roles

The task of event extraction contains subtasks including detections for entity mentions, event triggers and argument roles. Traditional methods solve them as a pipeline, which does not make use of task correlation for their mutual benefits. There have been recent efforts towards building a joint model for all tasks. However, due to technical challenges, there has not been work predicting the joint output structure as a single task. We build a first model to this end using a neural transition-based framework, incrementally predicting complex joint structures in a state-transition process. Results on standard benchmarks show the benefits of the joint model, which gives the best result in the literature.

scholarly journals Triple-VAE: A Triple Variational Autoencoder to Represent Events in One-Class Event Detection

2021 ◽  
Author(s):  
Marcos P. S. Gôlo ◽  
Rafael G. Rossi ◽  
Ricardo M. Marcacini
Keyword(s):  
Real World ◽  
Event Detection ◽  
Representation Learning ◽  
The Other ◽  
Specific Time ◽  
Variational Autoencoder ◽  
Significant Difference ◽  
The One ◽  
One Class Classification ◽  
Event Representations

Events are phenomena that occur at a specific time and place. Its detection can bring benefits to society since it is possible to extract knowledge from these events. Event detection is a multimodal task since these events have textual, geographical, and temporal components. Most multimodal research in the literature uses the concatenation of the components to represent the events. These approaches use multi-class or binary learning to detect events of interest which intensifies the user's labeling effort, in which the user should label event classes even if there is no interest in detecting them. In this paper, we present the Triple-VAE approach that learns a unified representation from textual, spatial, and density modalities through a variational autoencoder, one of the state-ofthe-art in representation learning. Our proposed Triple-VAE obtains suitable event representations for one-class classification, where users provide labels only for events of interest, thereby reducing the labeling effort. We carried out an experimental evaluation with ten real-world event datasets, four multimodal representation methods, and five evaluation metrics. Triple-VAE outperforms and presents a statistically significant difference considering the other three representation methods in all datasets. Therefore, Triple-VAE proved to be promising to represent the events in the one-class event detection scenario.

A Joint Model for Representation Learning of Tibetan Knowledge Graph Based on Encyclopedia

2021 ◽  
Vol 20 (2) ◽  
pp. 1-17
Author(s):  
Yuan Sun ◽  
Andong Chen ◽  
Chaofan Chen ◽  
Tianci Xia ◽  
Xiaobing Zhao
Keyword(s):  
Neural Networks ◽  
Language Processing ◽  
Representation Learning ◽  
Joint Model ◽  
Graph Representation ◽  
Knowledge Graph ◽  
High Resource ◽  
Complex Information ◽  
Language Knowledge ◽  
Knowledge Graphs

Learning the representation of a knowledge graph is critical to the field of natural language processing. There is a lot of research for English knowledge graph representation. However, for the low-resource languages, such as Tibetan, how to represent sparse knowledge graphs is a key problem. In this article, aiming at scarcity of Tibetan knowledge graphs, we extend the Tibetan knowledge graph by using the triples of the high-resource language knowledge graphs and Point of Information map information. To improve the representation learning of the Tibetan knowledge graph, we propose a joint model to merge structure and entity description information based on the Translating Embeddings and Convolution Neural Networks models. In addition, to solve the segmentation errors, we use character and word embedding to learn more complex information in Tibetan. Finally, the experimental results show that our model can make a better representation of the Tibetan knowledge graph than the baseline.

Sign in / Sign up

Export Citation Format

Share Document