Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Zuo, Xinyu"'
Fine-grained entity typing (FET) aims to deduce specific semantic types of the entity mentions in text. Modern methods for FET mainly focus on learning what a certain type looks like. And few works directly model the type differences, that is, let mo
Externí odkaz:
http://arxiv.org/abs/2208.10081
Current causal text mining datasets vary in objectives, data coverage, and annotation schemes. These inconsistent efforts prevent modeling capabilities and fair comparisons of model performance. Furthermore, few datasets include cause-effect span ann
Externí odkaz:
http://arxiv.org/abs/2208.09163
Autor:
Chen, Rui, Zuo, Xinyu, Bai, He, Qin, Ruolin, Chen, Zhiguo, Liu, Yiyun, Cao, Wenqing, Song, Jingpeng, Jia, Xiaoqiang
Publikováno v:
In Chinese Journal of Chemical Engineering October 2024 74:287-294
Publikováno v:
In Journal of Hydrology September 2024 641
Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLP-related augmentation methods cannot directly produce the available data requi
Externí odkaz:
http://arxiv.org/abs/2106.01649
Current models for event causality identification (ECI) mainly adopt a supervised framework, which heavily rely on labeled data for training. Unfortunately, the scale of current annotated datasets is relatively limited, which cannot provide sufficien
Externí odkaz:
http://arxiv.org/abs/2106.01654
Autor:
Miao, Jinyu, Zuo, Xinyu, McClements, David Julian, Zou, Liqiang, Liang, Ruihong, Zhang, Lu, Liu, Wei
Publikováno v:
In Journal of Food Engineering April 2024 366
Publikováno v:
COLING2020
Modern models of event causality detection (ECD) are mainly based on supervised learning from small hand-labeled corpora. However, hand-labeled training data is expensive to produce, low coverage of causal expressions and limited in size, which makes
Externí odkaz:
http://arxiv.org/abs/2010.10833
Causal explanation analysis (CEA) can assist us to understand the reasons behind daily events, which has been found very helpful for understanding the coherence of messages. In this paper, we focus on Causal Explanation Detection, an important subtas
Externí odkaz:
http://arxiv.org/abs/2009.10288
Publikováno v:
SCIENCE CHINA Information Sciences, Volume 62, Issue 11:212101(2019)
Event coreference resolution(ECR) is an important task in Natural Language Processing (NLP) and nearly all the existing approaches to this task rely on event argument information. However, these methods tend to suffer from error propagation from the
Externí odkaz:
http://arxiv.org/abs/2009.10290