Improving large language models in event relation logical prediction

M Chen, Y Ma, K Song, Y Cao… - Proceedings of the 62nd …, 2024 - aclanthology.org
Event relations are crucial for narrative understanding and reasoning. Governed by nuanced
logic, event relation extraction (ERE) is a challenging task that demands thorough semantic …

A graph propagation model with rich event structures for joint event relation extraction

J Zhang, T Chen, S Li, M Zhang, Y Ren… - Information Processing & …, 2024 - Elsevier
The task of event relation extraction (ERE) aims to organize multiple events and their
relations as a directed graph. However, existing ERE methods exhibit two limitations:(1) …

Learning to teach large language models logical reasoning

M Chen, Y Ma, K Song, Y Cao, Y Zhang… - arxiv preprint arxiv …, 2023 - arxiv.org
Large language models (LLMs) have gained enormous attention from both academia and
industry, due to their exceptional ability in language generation and extremely powerful …

Mastering context-to-label representation transformation for event causality identification with diffusion models

H Man, F Dernoncourt, TH Nguyen - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
To understand event structures of documents, event causality identification (ECI) emerges
as a crucial task, aiming to discern causal relationships among event mentions. The latest …

CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification

M Chen, Y Cao, Y Zhang, Z Liu - 2023 - ink.library.smu.edu.sg
Abstract Document-level Event Causality Identification (DECI) aims to recognize causal
relations between events within a document. Recent studies focus on building a document …

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 …

Zero-shot cross-lingual document-level event causality identification with heterogeneous graph contrastive transfer learning

Z He, P Cao, Z **, Y Chen, K Liu, Z Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Event Causality Identification (ECI) refers to the detection of causal relations between events
in texts. However, most existing studies focus on sentence-level ECI with high-resource …

CELLO: Causal Evaluation of Large Vision-Language Models

M Chen, B Peng, Y Zhang, C Lu - arxiv preprint arxiv:2406.19131, 2024 - arxiv.org
Causal reasoning is fundamental to human intelligence and crucial for effective decision-
making in real-world environments. Despite recent advancements in large vision-language …

Discriminative reasoning with sparse event representation for document-level event-event relation extraction

C Yuan, H Huang, Y Cao, Y Wen - 2023 - ink.library.smu.edu.sg
Abstract Document-level Event-Event Relation Extraction (DERE) aims to extract relations
between events in a document. It challenges conventional sentence-level task (SERE) with …

Prompt-based event relation identification with Constrained Prefix ATTention mechanism

H Zhang, W Ke, J Zhang, Z Luo, H Ma, Z Luan… - Knowledge-Based …, 2023 - Elsevier
Abstract Event Relation Identification (ERI) aims at mining the inter-event dependencies
expressed in event-mentioned sentences. The main challenge of this task lies in recognizing …