4 citations · 8 across the 8 of their papers we have counts for
6 papers · 1 filter
From Ultra-Fine to Fine: Fine-tuning Ultra-Fine Entity Typing Models to Fine-grained
Hongliang Dai, Ziqian Zeng
For the task of fine-grained entity typing (FET), due to the use of a large number of entity types, it is usually considered too costly to manually annotating a training dataset th…
Learning with Silver Standard Data for Zero-shot Relation Extraction
Tianyin Wang, Jianwei Wang, Ziqian Zeng
The superior performance of supervised relation extraction (RE) methods heavily relies on a large amount of gold standard data. Recent zero-shot relation extraction methods convert…
Weakly Supervised Text Classification using Supervision Signals from a Language Model
Ziqian Zeng, Weimin Ni, Tianqing Fang +3
Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked l…
Variational Weakly Supervised Sentiment Analysis with Posterior Regularization
Ziqian Zeng, Yangqiu Song
Sentiment analysis is an important task in natural language processing (NLP). Most of existing state-of-the-art methods are under the supervised learning paradigm. However, human a…
A Variational Approach to Unsupervised Sentiment Analysis
Ziqian Zeng, Wenxuan Zhou, Xin Liu +4
In this paper, we propose a variational approach to unsupervised sentiment analysis. Instead of using ground truth provided by domain experts, we use target-opinion word pairs as a…
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
Ziqian Zeng, Wenxuan Zhou, Xin Liu +1
In this paper, we propose a variational approach to weakly supervised document-level multi-aspect sentiment classification. Instead of using user-generated ratings or annotations p…