When does in-context learning fall short and why? a study on specification-heavy tasks

H Peng, X Wang, J Chen, W Li, Y Qi, Z Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
In-context learning (ICL) has become the default method for using large language models
(LLMs), making the exploration of its limitations and understanding the underlying causes …

MAVEN-ARG: Completing the puzzle of all-in-one event understanding dataset with event argument annotation

X Wang, H Peng, Y Guan, K Zeng, J Chen… - arxiv preprint arxiv …, 2023 - arxiv.org
Understanding events in texts is a core objective of natural language understanding, which
requires detecting event occurrences, extracting event arguments, and analyzing inter-event …

Document-level causal relation extraction with knowledge-guided binary question answering

Z Wang, L **a, W Wang, X Du - arxiv preprint arxiv:2410.04752, 2024 - arxiv.org
As an essential task in information extraction (IE), Event-Event Causal Relation Extraction
(ECRE) aims to identify and classify the causal relationships between event mentions in …

TextEE: Benchmark, reevaluation, reflections, and future challenges in event extraction

KH Huang, I Hsu, T Parekh, Z **e, Z Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
Event extraction has gained considerable interest due to its wide-ranging applications.
However, recent studies draw attention to evaluation issues, suggesting that reported scores …

CMNEE: a large-scale document-level event extraction dataset based on open-source Chinese military news

M Zhu, Z Xu, K Zeng, K **ao, M Wang, W Ke… - arxiv preprint arxiv …, 2024 - arxiv.org
Extracting structured event knowledge, including event triggers and corresponding
arguments, from military texts is fundamental to many applications, such as intelligence …

Beyond Exact Match: Semantically Reassessing Event Extraction by Large Language Models

YF Lu, XL Mao, T Lan, C Xu, H Huang - arxiv preprint arxiv:2410.09418, 2024 - arxiv.org
Event extraction has gained extensive research attention due to its broad range of
applications. However, the current mainstream evaluation method for event extraction relies …

Argument-Aware Approach To Event Linking

I Hsu, Z Xue, N Pochh, S Bansal, P Natarajan… - arxiv preprint arxiv …, 2024 - arxiv.org
Event linking connects event mentions in text with relevant nodes in a knowledge base (KB).
Prior research in event linking has mainly borrowed methods from entity linking, overlooking …

Prompt-Based Event Coreference Resolution on Multi-dimensional Information and Auxiliary Tasks

H Zhong, S Xu, P Li, Q Zhu - International Conference on Intelligent …, 2024 - Springer
Abstract Event Coreference Resolution (ECR) aims to group same event mentions into a
cluster. Previous work on capturing multi-dimensional event information focused on rule …

Thematic Event Clustering and Storyline Analysis Based on Multi-source Heterogeneous Chinese International Negotiation Documents

Q Zhang, J Wu, M Zhu, X Li, L Qian… - 2024 10th International …, 2024 - ieeexplore.ieee.org
In the international relations and foreign policy research, international negotiation data is of
great importance for assisting scholars in analyzing patterns of interaction between nations …

[PDF][PDF] Knowledge Base-enhanced Multilingual Relation Extraction with Large Language Models

T Chen, P Sen, Z Wang, Z Jiang, J Su - 2024 - ceur-ws.org
Relation Extraction (RE) is an essential task that involves comprehending relational facts
between entities from natural language texts. However, existing research in RE, particularly …