10 citations · 34 across the 7 of their papers we have counts for
7 papers
Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing
Xinyu Zuo, Haijin Liang, Ning Jing +3
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 li…
UniCausal: Unified Benchmark and Repository for Causal Text Mining
Fiona Anting Tan, Xinyu Zuo, See-Kiong Ng
Current causal text mining datasets vary in objectives, data coverage, and annotation schemes. These inconsistent efforts prevent modeling capabilities and fair comparisons of mode…
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
Xinyu Zuo, Pengfei Cao, Yubo Chen +4
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 an…
LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification
Xinyu Zuo, Pengfei Cao, Yubo Chen +4
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…
KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision
Xinyu Zuo, Yubo Chen, Kang Liu +1
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 produc…
Towards Causal Explanation Detection with Pyramid Salient-Aware Network
Xinyu Zuo, Yubo Chen, Kang Liu +1
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 thi…
Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information
Xinyu Zuo, Yubo Chen, Kang Liu +1
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.…