Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Applied Sciences  /  Vol: 13 Par: 13 (2023)  /  Artículo
ARTÍCULO
TITULO

An Open-Domain Event Extraction Method Incorporating Semantic and Dependent Syntactic Information

Li He    
Qian Zhang    
Jianyong Duan and Hao Wang    

Resumen

Open-domain event extraction is a fundamental task that aims to extract non-predefined types of events from news clusters. Some researchers have noticed that its performance can be enhanced by improving dependency relationships. Recently, graphical convolutional networks (GCNs) have been widely used to integrate dependency syntactic information into neural networks. However, they usually introduce noise and deteriorate the generalization. To tackle this issue, we propose using Bi-LSTM to obtain semantic representations of BERT intermediate layer features and infuse the dependent syntactic information. Compared to current methods, Bi-LSTM is more robust and has less dependency on word vectors and artificial features. Experiments on public datasets show that our approach is effective for open-domain event extraction tasks.

 Artículos similares

       
 
Inkyu Choi, Soo Hyun Bae and Nam Soo Kim    
Audio event detection (AED) is a task of recognizing the types of audio events in an audio stream and estimating their temporal positions. AED is typically based on fully supervised approaches, requiring strong labels including both the presence and temp... ver más
Revista: Applied Sciences

 
Karina Hauser, Helgi S. Sigurdsson, Katherine M. Chudoba    
Enterprise Applications are difficult to implement and maintain because they require a monolith of code to incorporate required business processes. Service-oriented architecture is one solution, but challenges of dependency and software complexity remain... ver más