April 3, 2024, 4:46 a.m. | Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, Yulan He

cs.CL updates on arXiv.org arxiv.org

arXiv:2404.01532v1 Announce Type: new
Abstract: Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs for constructing event temporal graphs, have shown promising results. However, these methods have often led to suboptimal graph generation as the linearised graphs exhibit set characteristics which are instead treated sequentially by language models. This discrepancy stems from the conventional text generation objectives, leading …

abstract arxiv auto cs.cl cs.ir event events framework generate graph graphs however language language models relations results set studies temporal text type

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Snowflake Analytics Engineer - Technology Sector

@ Winning | Lisbon, Lisbon

Business Data Analyst

@ RideCo | Waterloo, Ontario, Canada

Senior Data Scientist, Payment Risk

@ Block | Boston, MA, United States

Research Scientist, Data Fusion (Climate TRACE)

@ WattTime | Remote

Technical Analyst (Data Analytics)

@ Contact Government Services | Fayetteville, AR