Semi-Supervised Event Extraction with Paraphrase Clusters

Ferguson, James F.; Lockard, Colin; Weld, Daniel S.; Hajishirzi, Hannaneh

doi:10.18653/v1/n18-2058

Cited by 36 publications

(20 citation statements)

References 9 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They can extract high-quality event mentions for the given types, but cannot extract mentions for any new types. Recent studies Chan et al, 2019;Ferguson et al, 2018) leverage annotations for a few seen event types or several keywords provided for the new types to extract mentions for new types. However, all these studies assume all the target types are given, which is very costly when moving to a new scenario.…”

Section: Related Workmentioning

confidence: 99%

Semi-supervised New Event Type Induction and Event Detection

Huang¹,

Ji²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Most previous event extraction studies assume a set of target event types and corresponding event annotations are given, which could be very expensive. In this paper, we work on a new task of semi-supervised event type induction, aiming to automatically discover a set of unseen types from a given corpus by leveraging annotations available for a few seen types. We design a Semi-Supervised Vector Quantized Variational Autoencoder framework to automatically learn a discrete latent type representation for each seen and unseen type and optimize them using seen type event annotations. A variational autoencoder is further introduced to enforce the reconstruction of each event mention conditioned on its latent type distribution. Experiments show that our approach can not only achieve state-of-the-art performance on supervised event detection but also discover high-quality new event types. 1

show abstract

Section: Related Workmentioning

confidence: 99%

Semi-supervised New Event Type Induction and Event Detection

Huang¹,

Ji²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…and Zeng et al (2018) use distant supervision to generate largescale data from existing structured event knowledge in knowledge bases. Liao and Grishman (2010a), Huang and Riloff (2012a) and Ferguson et al (2018) conduct semi-supervised ED with bootstrapping. Nevertheless, due to the low coverage of existing knowledge bases as well as lack of advanced denoising mechanism, those weakly supervised methods still suffer from the problem of low coverage and noisy data.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Training for Weakly Supervised Event Detection

Wang

Han

Liu

et al. 2019

Proceedings of the 2019 Conference of the North

116

View full text Add to dashboard Cite

Modern weakly supervised methods for event detection (ED) avoid time-consuming human annotation and achieve promising results by learning from auto-labeled data. However, these methods typically rely on sophisticated pre-defined rules as well as existing instances in knowledge bases for automatic annotation and thus suffer from low coverage, topic bias, and data noise. To address these issues, we build a large event-related candidate set with good coverage and then apply an adversarial training mechanism to iteratively identify those informative instances from the candidate set and filter out those noisy ones. The experiments on two real-world datasets show that our candidate selection and adversarial training can cooperate together to obtain more diverse and accurate training data for ED, and significantly outperform the state-of-theart methods in various weakly supervised scenarios. The datasets and source code can be obtained from https://github.com/ thunlp/Adv-ED.

show abstract

“…As events have complicated structures, like different event types containing different arguments with different roles, computing event extraction confidence is normally with low accuracies. Liao and Grishman [209], [210] proposed to use only a part of extraction results from new samples for data expansion, in particular, the most confident trigger with its most confident argument. Based on their extraction model [94], the most confident ''<role, trigger>'' pairs are selected based on the product between probability from their trigger classifier and argument classifier.…”

Section: A Joint Data Expansion and Model Trainingmentioning

confidence: 99%

A Survey of Event Extraction From Text

2019

View full text Add to dashboard Cite

Numerous important events happen everyday and everywhere but are reported in different media sources with different narrative styles. How to detect whether real-world events have been reported in articles and posts is one of the main tasks of event extraction. Other tasks include extracting event arguments and identifying their roles, as well as clustering and tracking similar events from different texts. As one of the most important research themes in natural language processing and understanding, event extraction has a wide range of applications in diverse domains and has been intensively researched for decades. This article provides a comprehensive yet up-to-date survey for event extraction from text. We not only summarize the task definitions, data sources and performance evaluations for event extraction, but also provide a taxonomy for its solution approaches. In each solution group, we provide detailed analysis for the most representative methods, especially their origins, basics, strengths and weaknesses. Last, we also present our envisions about future research directions. INDEX TERMS Event extraction, event extraction tasks, event corpus, natural language processing.

show abstract

Semi-Supervised Event Extraction with Paraphrase Clusters

Cited by 36 publications

References 9 publications

Semi-supervised New Event Type Induction and Event Detection

Semi-supervised New Event Type Induction and Event Detection

Adversarial Training for Weakly Supervised Event Detection

A Survey of Event Extraction From Text

Contact Info

Product

Resources

About