This repository is a curated collection of academic papers on deep learning-based event extraction, primarily from 2015 onwards. It serves researchers and practitioners in Natural Language Processing (NLP) by organizing key publications, categorizing them by sub-fields like open-domain, cross-lingual, and few-shot event extraction, and annotating them with keywords and model abbreviations. The collection aims to provide a comprehensive overview of the state-of-the-art in this NLP sub-task.

How It Works

The repository functions as a literature review and catalog. It lists papers with their authors, URLs to their publications (often ACL Anthology or arXiv), associated datasets (e.g., ACE2005, KBP2015), and relevant keywords highlighting the core techniques or contributions. The categorization helps users navigate the landscape of event extraction research, from foundational CNN and RNN approaches to more recent transformer-based and specialized methods.

Quick Start & Requirements

This repository is a collection of research papers and does not contain executable code for event extraction. To utilize the information, users would need to access the linked papers and potentially implement the described methods.

Highlighted Details

• Comprehensive coverage of event extraction research from 2015 to 2022, including major NLP conferences (ACL, EMNLP, NAACL, AAAI, IJCAI, COLING, WWW, SIGIR, CIKM).
• Categorization into key sub-areas: Chinese Event Extraction, Open-domain Event Extraction, Event Data Generation, Cross-lingual Event Extraction, Few-Shot Event Extraction, Zero-Shot Event Extraction, Document-level EE, and more.
• Detailed metadata for each paper, including authors, publication venue, dataset used, and technical keywords (e.g., CNN, RNN, LSTM, GCN, BERT, Transformers, Attention Mechanisms, GANs).
• Inclusion of papers focusing on specific challenges like implicit event detection, argument extraction, event coreference, and temporal relation extraction.

Maintenance & Community

The repository is maintained by carrie0307. There is no explicit mention of community channels or active development beyond the curation of papers.

Licensing & Compatibility

The repository itself does not have a specified license. It is a collection of links to academic papers, each with its own publication and distribution terms. Compatibility for commercial use would depend on the licenses of the individual papers and their respective publishers.

Limitations & Caveats

This repository is a curated list of papers and does not provide code, datasets, or benchmarks for direct use. The accuracy and completeness of the annotations (keywords, categories) are subject to the curator's interpretation, and omissions or mistakes may exist as stated in the README.