no code implementations • EMNLP 2020 • Wenlin Yao, Zeyu Dai, Maitreyi Ramaswamy, Bonan Min, Ruihong Huang
We first obtain the initial set of event pairs that are likely to have the subevent relation, by exploiting two observations that 1) subevents are temporally contained by the parent event, and 2) the definitions of the parent event can be used to further guide the identification of subevents.
no code implementations • 19 Jun 2023 • Rui He, Zeyu Dai, Shan He, Ke Tang
Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of highly informative instances, thereby reducing the labeling effort.
no code implementations • 4 Jul 2022 • Xueying Zhan, Zeyu Dai, Qingzhong Wang, Qing Li, Haoyi Xiong, Dejing Dou, Antoni B. Chan
In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.
1 code implementation • 4 Jun 2022 • Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li
In this paper, we propose to restrict the perturbations to a small salient region to generate adversarial examples that can hardly be perceived.
no code implementations • 29 Sep 2021 • Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li
To address this issue, in this paper we propose to use segmentation priors for black-box attacks such that the perturbations are limited in the salient region.
no code implementations • IJCNLP 2019 • Zeyu Dai, Ruihong Huang
We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing.
1 code implementation • EMNLP 2018 • Zeyu Dai, Ruihong Huang
Capabilities to categorize a clause based on the type of situation entity (e. g., events, states and generic statements) the clause introduces to the discourse can benefit many NLP applications.
no code implementations • COLING 2018 • Zeyu Dai, Himanshu Taneja, Ruihong Huang
Journalists usually organize and present the contents of a news article following a well-defined structure.
no code implementations • NAACL 2018 • Zeyu Dai, Ruihong Huang
We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure.
General Classification Implicit Discourse Relation Classification +2
no code implementations • IJCNLP 2017 • Zeyu Dai, Wenlin Yao, Ruihong Huang
Focusing on the task of identifying event temporal status, we find that events directly or indirectly governing the target event in a dependency tree are most important contexts.
no code implementations • RANLP 2017 • Wenlin Yao, Zeyu Dai, Ruihong Huang, James Caverlee
The lack of large realistic datasets presents a bottleneck in online deception detection studies.