Exploring Pre-trained Language Models for Event Extraction and Generation

Yang, Sen; Feng, Dawei; Qiao, Linbo; Kan, Zhigang; Li, Dongsheng

doi:10.18653/v1/p19-1522

Cited by 262 publications

(165 citation statements)

References 18 publications

Supporting

Mentioning

165

Contrasting

Order By: Relevance

“…Thanks to the powerful language expression capabilities of the BERT model, a few layers of simple fully connected networks can achieve good results in the trigger extraction subtask. We follow previous research work [13] to obtain triggers, and then assign argument roles via EE-DGCNN proposed in this paper.…”

Section: Methodsmentioning

confidence: 99%

“…After the pre-trained language model appeared, its ability to express semantic information attracted the attention of researchers in the field of event extraction. The PLMEE [13] method proposed by Yang et al applied a pre-trained language model as a method to capture word features directly and obtained a large performance improvement.…”

Section: Related Work a Event Extractionmentioning

confidence: 99%

“…We evaluate our model with the ACE 2005 corpus. To verify the effectiveness of our EE-DGCNN model, we follow the data partitioning methods of previous research work [3], [9], [11]- [13], [25]. The test set of the experiment is composed of 40 newswire articles, while the validation set is 30 other documents from newswire.…”

Section: B Dataset and Evaluation Metricmentioning

confidence: 99%

See 2 more Smart Citations

Event Arguments Extraction via Dilate Gated Convolutional Neural Network With Enhanced Local Features

et al. 2020

Self Cite

View full text Add to dashboard Cite

Event Extraction plays an important role in information-extraction to understand the world. Event extraction could be split into two subtasks: one is event trigger extraction, the other is event arguments extraction. However, the F1-Score of event arguments extraction is much lower than that of event trigger extraction, i.e. in the most recent work, event trigger extraction achieves 80.7%, while event arguments extraction achieves only 58%. In pipelined structures, the difficulty of event arguments extraction lies in its lack of classification feature, and the much higher computation consumption. In this work, we proposed a novel Event Extraction approach based on multi-layer Dilate Gated Convolutional Neural Network (EE-DGCNN) which has fewer parameters. In addition, enhanced local information is incorporated into word features, to assign event arguments roles for triggers predicted by the first subtask. The numerical experiments demonstrated significant performance improvement beyond state-of-art event extraction approaches on real-world datasets. Further analysis of extraction procedure is presented, as well as experiments are conducted to analyze impact factors related to the performance improvement.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Work a Event Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Event Arguments Extraction via Dilate Gated Convolutional Neural Network With Enhanced Local Features

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…[1] describes a novel training setup called matching the blanks, and couple it with BERT [6] to produce useful relation representations, particularly effective in low-resource regimes. [33] proposes a method to automatically generate labeled data by editing prototypes and screen out generated samples by ranking the quality.…”

Section: Related Work 21 Sample Shortage Problems In Ed Tasksmentioning

confidence: 99%

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

Deng

Zhang

Kang

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are unfortunately not readily available in many real-life applications. In this paper, we consider and reformulate the ED task with limited labeled data as a Few-Shot Learning problem. We propose a Dynamic-Memory-Based Prototypical Network (DMB-PN), 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. Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs. The experiments show that DMB-PN not only deals with sample scarcity better than a series of baseline models but also performs more robustly when the variety of event types is relatively large and the instance quantity is extremely small.

show abstract

“…• PLMEE [46]: a pipelined method using BERT as backbones. • Joint3EE [47]: a joint method that perform predictions for entity mentions, event triggers and argument based on the sharing hidden representations.…”

Section: Overall Performancementioning

confidence: 99%

A Question Answering-Based Framework for One-Step Event Argument Extraction

Zhang

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Event argument extraction, which aims to identify arguments of specific events and label their roles, is a challenging subtask of event extraction. Previous approaches solve this problem in a twostage manner that first extracts named entities as argument candidates and then determines their roles. However, many nested entities may be missed or wrongly predicted during the argument candidate extraction procedure, which substantially affects the performance of the downstream classifier. In this paper, we propose a novel one-step question answering based framework, which performs argument candidate extraction and argument role classification simultaneously to mitigate the error propagation problem in conventional two-stage methods. Since the conventional question answering based framework cannot be applied directly to this task, we design a Question Answering based Sequence Labeling (QA-SL) model to tackle inexistent argument roles and multiple argument token spans. Moreover, considering the overwhelming number of parameters in question answering based neural network models and the relatively small size of event extraction corpus, we fine-tune the pre-trained model from BERT to mitigate the data scarcity problem. Extensive experiments demonstrate the benefits of the proposed method, leading to a competitive performance compared with state-of-the-art methods. To the best of our knowledge, this is the first work to cast event argument extraction as a question answering task.

show abstract

Exploring Pre-trained Language Models for Event Extraction and Generation

Cited by 262 publications

References 18 publications

Event Arguments Extraction via Dilate Gated Convolutional Neural Network With Enhanced Local Features

Event Arguments Extraction via Dilate Gated Convolutional Neural Network With Enhanced Local Features

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

A Question Answering-Based Framework for One-Step Event Argument Extraction

Contact Info

Product

Resources

About