Deep learning for Event Extraction事件抽取(Event Extraction, EE)是NLP领域中一种经典的信息抽取任务,在商业、军事等领域的情报工作中应用非常广泛。从理论发展的角度看,事件抽取的相关研究,有助于我们深入了解任机器理解数据、理解世界的机制,也有助于我们了解自身的认知机制,作为一种方法对人工智能之外领域的研究也是非常有意义的。从应用的角度看,事件抽取技术可以帮助我们解决很多现实问题,比如前面提到的海量信息的自动处理。而近年来,深度学习技术的发展,使得事件抽取的水平有了大幅度的提升。
Shankai Yan,Ka-Chun Wong
BIOINFORMATICS, no. 2 (2020): 637-643
Motivation: Biomedical event extraction is fundamental for information extraction in molecular biology and biomedical research. The detected events form the central basis for comprehensive biomedical knowledge fusion, facilitating the digestion of massive information influx from ...
Cited by3BibtexViews63DOI
0
0
Shumin Deng,Ningyu Zhang, Jiaojian Kang, Yichi Zhang,Wei Zhang,Huajun Chen
WSDM '20: The Thirteenth ACM International Conference on Web Search and Data Mining Houston ..., pp.151-159, (2020)
We propose a Dynamic-Memory-Based Prototypical Network, which exploits Dynamic Memory Network to learn better prototypes for event types, and produce more robust sentence encodings for event mentions
Cited by0BibtexViews172DOI
0
0
north american chapter of the association for computational linguistics, (2019)
By incorporating external knowledge base information, our approach achieves about 2.12% F-score gain comparing to Tree-LSTM, which demonstrates the effectiveness of the knowledge bases properties for biomedical event extraction
Cited by25BibtexViews206
0
0
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF AR..., pp.6754-6761, (2019)
The ambiguity in language expressions poses a great challenge for event detection. To disambiguate event types, current approaches rely on external NLP toolkits to build knowledge representations. Unfortunately, these approaches work in a pipeline paradigm and suffer from error p...
Cited by19BibtexViews134
0
0
Haoran Yan,Xiaolong Jin, Xiangbin Meng,Jiafeng Guo,Xueqi Cheng
EMNLP/IJCNLP (1), pp.5765-5769, (2019)
Cited by16BibtexViews209DOI
0
0
Trung Minh Nguyen, Thien Huu Nguyen
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF AR..., (2019): 6851-6858
We achieve the state-of-the-art performance for event extraction with predicted entity mentions
Cited by14BibtexViews129
0
0
EMNLP/IJCNLP (1), pp.5776-5782, (2019)
We propose a hierarchical modular event argument extraction model, which adopts flexible modular networks to utilize the hierarchical concept correlation among argument roles as effective inductive bias
Cited by12BibtexViews356DOI
0
0
David Wadden, Ulme Wennberg, Yi Luan,Hannaneh Hajishirzi
EMNLP/IJCNLP (1), pp.5783-5788, (2019)
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans des...
Cited by11BibtexViews182DOI
0
0
Ning Ding,Ziran Li,Zhiyuan Liu, Haitao Zheng, Zibo Lin
EMNLP/IJCNLP (1), pp.347-356, (2019)
We propose a novel framework Trigger-aware Lattice Neural Network for event detection, which can simultaneously address the problems of trigger-word mismatch and polysemous triggers
Cited by11BibtexViews195DOI
0
0
EMNLP/IJCNLP (1), pp.282-291, (2019)
To extract the structured representations of open-domain events, Bayesian graphical models have made some progress. However, these approaches typically assume that all words in a document are generated from a single event. While this may be true for short text such as tweets, s...
Cited by8BibtexViews191DOI
0
0
Ananya Subburathinam,Di Lu,Heng Ji,Jonathan May,Shih-Fu Chang, Avirup Sil,Clare Voss
EMNLP/IJCNLP (1), pp.313-325, (2019)
Cited by5BibtexViews290DOI
0
0
EMNLP/IJCNLP (1), pp.434-444, (2019)
We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction. The proposed method has two advantages over existing work. First, it improves event representation by allowing the event and relation modules to share ...
Cited by2BibtexViews170DOI
0
0
Hongyu Lin, Yaojie Lu,Xianpei Han,Le Sun
ACL (1), pp.5278-5283, (2019)
In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type. To address this label confusion problem, this paper proposes cost-sensitive regularization, w...
Cited by0BibtexViews83DOI
0
0
Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan,Dongsheng Li
ACL (1), pp.5284-5294, (2019)
Cited by0BibtexViews60DOI
0
0
Mohammed Aldawsari, Mark Finlayson
ACL (1), pp.4780-4790, (2019)
Cited by0BibtexViews34DOI
0
0
ACL, no. 9 (2018)
We introduce a hybrid neural network model, which incorporates both bidirectional LSTMs and convolutional neural networks to capture sequence and structure semantic information from specific contexts, for event detection
Cited by176BibtexViews187DOI
0
0
Thien Huu Nguyen,Ralph Grishman
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTI..., pp.5900-5907, (2018)
We propose a novel neural network model for event detection that is based on graph convolutional networks over dependency trees and entity mention-guided pooling
Cited by124BibtexViews137
0
0
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTI..., pp.4865-4872, (2018)
Identifying event instance in text plays a critical role in building NLP applications such as Information Extraction (IE) system. However, most existing methods for this task focus only on monolingual clues of a specific language and ignore the massive information provided by oth...
Cited by61BibtexViews174
0
0
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTI..., pp.5916-5923, (2018)
This paper proposes a novel deep neural network architecture, called dependency-bridge recurrent neural network for the task of event extraction. dependency bridge recurrent neural network introduces dependency bridges to recurrent neural networks so that syntactical information ...
Cited by48BibtexViews224
0
0
小科