Výsledky vyhledávání - "Yang, Huiyun"

Report

FOAL: Fine-grained Contrastive Learning for Cross-domain Aspect Sentiment Triplet Extraction

Autor: Xu, Ting, Wu, Zhen, Yang, Huiyun, Dai, Xinyu

Aspect Sentiment Triplet Extraction (ASTE) has achieved promising results while relying on sufficient annotation data in a specific domain. However, it is infeasible to annotate data for each individual domain. We propose to explore ASTE in the cross

Externí odkaz: http://arxiv.org/abs/2311.10373

Zobrazit plný text záznamu

Report

Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction

Autor: Xu, Ting, Yang, Huiyun, Wu, Zhen, Chen, Jiaze, Zhao, Fei, Dai, Xinyu

Aspect Sentiment Triplet Extraction (ASTE) is widely used in various applications. However, existing ASTE datasets are limited in their ability to represent real-world scenarios, hindering the advancement of research in this area. In this paper, we i

Externí odkaz: http://arxiv.org/abs/2305.17448

Zobrazit plný text záznamu

Report

Enhancing Cross-lingual Transfer by Manifold Mixup

Autor: Yang, Huiyun, Chen, Huadong, Zhou, Hao, Li, Lei

Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances. However, the performance of target languages still lags far behind the source language. In this paper

Externí odkaz: http://arxiv.org/abs/2205.04182

Zobrazit plný text záznamu