Challenge: Recent work on Event Extraction addresses the error propagation issue found in token-based classification approaches.
Approach: They propose a Question Generation (QG) model that generates questions that leverage contextual information instead of fixed templates.
Outcome: The proposed model outperforms all previous single-task-based models on the ACE05 English dataset.

Similar Papers

Towards Better Question Generation in QA-based Event Extraction (2024.findings-acl)

Copied to clipboard

Challenge: True. True. EE aims to extract event-related information from unstructured texts.
Approach: They propose a reinforcement learning method that evaluates the quality of a question and provides clear guidance to QA models.
Outcome: The proposed method generates generalizable, high-quality, and context-dependent questions and provides clear guidance to QA models.
Event Extraction by Answering (Almost) Natural Questions (2020.emnlp-main)

Copied to clipboard

Challenge: Existing work in event argument extraction relies heavily on entity recognition as a preprocessing/concurrent step, causing error propagation.
Approach: They propose a question answering task that extracts event arguments in an end-to-end manner.
Outcome: The proposed framework outperforms prior work on the ACE 2005 task on event argument extraction.
Retrieval-Augmented Generative Question Answering for Event Argument Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to extract arguments from documents are based on generating and post-processing a complex target sequence (template).
Approach: They propose a retrieval-augmented generative QA model that retrieves the most similar QA pair and augments it as prompt to the current example's context, then decodes the arguments as answers.
Outcome: The proposed model outperforms prior methods across fully supervised, domain transfer, and fewshot learning settings and compares with clustering-based sampling strategies.
QAEVENT: Event Extraction as Question-Answer Pairs Generation (2024.findings-eacl)

Copied to clipboard

Challenge: a novel approach to document-level event extraction requires linguistic expertise.
Approach: They propose a question-and-answer-pair representation of document-level events as question and answer pairs (QAEVENT) this allows for more scalable and faster annotations from crowdworkers without linguistic expertise.
Outcome: The proposed method produces high-quality data for document-level event extraction compared to pre-defined schemas . it is scalable and faster than existing methods, with no linguistic expertise.
Asking and Answering Questions to Extract Event-Argument Structures (2024.lrec-main)

Copied to clipboard

Challenge: Traditionally, corpora are limited to arguments within the same sentence, and inter-sentential arguments are more challenging and have received less attention.
Approach: They propose a question-answering approach to extract document-level event-argument structures by automating questions for each argument type an event may have.
Outcome: The proposed model outperforms previous models and is especially beneficial to extract arguments that appear in different sentences than the event trigger.
Exploring Pre-trained Language Models for Event Extraction and Generation (P19-1)

Copied to clipboard

Challenge: Existing methods to extract event data are laborious to create and limited in size.
Approach: They propose an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles.
Outcome: The proposed method surpasses existing methods on the ACE2005 dataset and improves on the previous methods.
Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for document-level argument extraction do not require human involvement and combine uncontextualized and contextualized questions.
Approach: They propose multiple question generation strategies for document-level event argument extraction that do not require human involvement and combine uncontextualized and contextualized questions.
Outcome: The proposed questions do not require human involvement and are suitable for document-level argument extraction.
Document-Level Event Argument Extraction by Conditional Generation (2021.naacl-main)

Copied to clipboard

Challenge: Existing event extraction models have been limited to the sentence level . this formulation signifies a misalignment between the information seeking behavior and the informative seeking behavior.
Approach: They propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates.
Outcome: The proposed model achieves 7.6% F1 and 5.7% F1 over the best baseline on the document-level event extraction dataset WikiEvents and 9.3% F1 on the informative argument extraction task.
Demonstration Retrieval-Augmented Generative Event Argument Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Experimental results show that our method outperforms all strong baselines and can be generalized to various datasets.
Approach: They propose a generative EAE that uses event knowledge-injected generator and demonstration retriever to generate event arguments from training data.
Outcome: The proposed method outperforms baselines and can be generalized to various datasets.
Event Extraction as Multi-turn Question Answering (2020.findings-emnlp)

Copied to clipboard

Challenge: Current approaches to event extraction fail to model rich interactions among event types and arguments of different roles.
Approach: They propose a new paradigm that formulates event extraction as multi-turn question answering . they propose to use reading comprehension problems to extract triggers and arguments .
Outcome: The proposed approach outperforms current state-of-the-art on argument extraction tasks . it makes full use of dependency among arguments and event types, and generalizes well .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations