Reading the Manual: Event Extraction as Definition Comprehension

Chen, Yunmo; Chen, Tongfei; Ebner, Seth; White, Aaron Steven; Durme, Benjamin Van

doi:10.48550/arxiv.1912.01586

Cited by 4 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our major findings from the experiments are: (1) Our proposed approach of formulating event extraction as reading comprehension can effectively distill knowledge by probing pre-trained models, and achieve strong performance for zero-shot event detection without training data. (2) The performance of our model increases largely when the model is fed a small amount of labeled data. In fullysupervised settings, it achieve state-of-the-art performance.…”

Section: Queries On Argumentsmentioning

confidence: 99%

“…Comparing with existing works, our framework is more capable in exploiting pre-trained reading comprehension models on tasks and event semantics. (2) We are the first to propose a reading comprehension framework of event detection and argument detection without trigger words. (3) By probing and fine-tuning pretrained reading comprehension models, our approach achieves much stronger performance for low-shot event extraction compared with the baselines; and it achieves state-of-the-art performance for fullysupervised event detection on the ACE 2005 benchmark.…”

Section: Queries On Argumentsmentioning

confidence: 99%

“…BERT [8] model is a masked language model that consists of deep multihead attention layers. Given a pair of input sentences 𝑋 (1) , 𝑋 (2) , BERT first runs WordPiece [38] tokenizer to tokenize the both sentences into a sequence of token ids:…”

Section: Model Detailsmentioning

confidence: 99%

“…[12] probed whether or when the format of question answering is useful. [2] designed a pipeline to do zero-shot event detection by reading information from the annotation guide.…”

Section: Reading Comprehension Frameworkmentioning

confidence: 99%

“…Formulating tasks as machine reading comprehension has one key advantage, that it is able to better utilize knowledge in modern language models, such as BERT [8], ideally improving label efficiency. For example, among above mentioned works, [2,18,32,42] all employed reading comprehension as a tool for zero-or few-shot learning.…”

Section: Reading Comprehension Frameworkmentioning

confidence: 99%

See 4 more Smart Citations

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

Feng,

Yuan,

Zhang

2020

Preprint

View full text Add to dashboard Cite

We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervised sequence labeling problems. We argue that the event extraction models so trained are inherently labelhungry, and can generalize poorly across domains and text genres. We propose a reading comprehension framework for event extraction. Specifically, we formulate event detection as a textual entailment prediction problem, and argument detection as a question answering problem. By constructing proper query templates, our approach can effectively distill rich knowledge about tasks and label semantics from pretrained reading comprehension models. Moreover, our model can be fine-tuned with a small amount of data to boost its performance. Our experiment results show that our method performs strongly for zero-shot and few-shot event extraction, and it achieves state-of-the-art performance on the ACE 2005 benchmark when trained with full supervision.

show abstract

Section: Queries On Argumentsmentioning

confidence: 99%

Section: Queries On Argumentsmentioning

confidence: 99%

Section: Model Detailsmentioning

confidence: 99%

“…[12] probed whether or when the format of question answering is useful. [2] designed a pipeline to do zero-shot event detection by reading information from the annotation guide.…”

Section: Reading Comprehension Frameworkmentioning

confidence: 99%

Section: Reading Comprehension Frameworkmentioning

confidence: 99%

See 3 more Smart Citations

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

Feng,

Yuan,

Zhang

2020

Preprint

View full text Add to dashboard Cite

show abstract

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

Wang¹,

Yu²,

Chang³

et al. 2022

Findings of the Association for Computational Linguistics: ACL 2022

View full text Add to dashboard Cite

Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols. These approaches are usually limited to a set of pre-defined types. We propose a novel event extraction framework that uses event types and argument roles as natural language queries to extract candidate triggers and arguments from the input text. With the rich semantics in the queries, our framework benefits from the attention mechanisms to better capture the semantic correlation between the event types or argument roles and the input text. Furthermore, the query-and-extract formulation allows our approach to leverage all available event annotations from various ontologies as a unified model. Experiments on ACE and ERE demonstrate that our approach achieves state-of-the-art performance on each dataset and significantly outperforms existing methods on zero-shot event extraction. 1

show abstract

Movie Scene Event Extraction with Graph Attention Network Based on Argument Correlation Information

Qian

Zhang

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Movie scene event extraction is a practical task in media analysis, which aims at extracting structured events from unstructured movie scripts. However, although there have been many studies regarding open domain event extraction, there have only been a few studies focusing on movie scene event extraction. Specifically aimed at instances where different argument roles have the same characteristics in a movie scene, we propose the utilization of the correlation between different argument roles, which is beneficial for both movie scene trigger extraction (trigger identification and classification) and movie scene argument extraction (argument identification and classification) in event extraction. To model the correlation between different argument roles, we propose the superior role concept (SRC), a high-level role concept based upon the ordinary argument role. In this paper, we introduce a new movie scene event extraction model with two main features: (1) an attentive high-level argument role module to capture SRC information and (2) an SRC-based graph attention network (GAT) to fuse the argument role correlation information into semantic embeddings. To evaluate the performance of our model, we constructed a movie scene event extraction dataset named MovieSceneEvent and also conducted experiments on a widely used dataset to compare the results with other models. The experimental results show that our model outperforms competitive models, and the correlation information of argument roles helps to improve the performance of movie scene event extraction.

show abstract

Reading the Manual: Event Extraction as Definition Comprehension

Cited by 4 publications

References 26 publications

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

Movie Scene Event Extraction with Graph Attention Network Based on Argument Correlation Information

Contact Info

Product

Resources

About