Ping Chen


Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning
Wenbin An | Feng Tian | Ping Chen | Siliang Tang | Qinghua Zheng | QianYing Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of the same granularity.In this paper, we investigate a new practical scenario called Fine-grained Category Discovery under Coarse-grained supervision (FCDC). FCDC aims at discovering fine-grained categories with only coarse-grained labeled data, which can adapt models to categories of different granularity from known ones and reduce significant labeling cost. It is also a challenging task since supervised training on coarse-grained categories tends to focus on inter-class distance (distance between coarse-grained classes) but ignore intra-class distance (distance between fine-grained sub-classes) which is essential for separating fine-grained categories.Considering most current methods cannot transfer knowledge from coarse-grained level to fine-grained level, we propose a hierarchical weighted self-contrastive network by building a novel weighted self-contrastive module and combining it with supervised learning in a hierarchical manner.Extensive experiments on public datasets show both effectiveness and efficiency of our model over compared methods.


Contrastive Learning of Sentence Representations
Hefei Qiu | Wei Ding | Ping Chen
Proceedings of the 18th International Conference on Natural Language Processing (ICON)

Learning sentence representations which capture rich semantic meanings has been crucial for many NLP tasks. Pre-trained language models such as BERT have achieved great success in NLP, but sentence embeddings extracted directly from these models do not perform well without fine-tuning. We propose Contrastive Learning of Sentence Representations (CLSR), a novel approach which applies contrastive learning to learn universal sentence representations on top of pre-trained language models. CLSR utilizes semantic similarity of two sentences to construct positive instance for contrastive learning. Semantic information that has been captured by the pre-trained models is kept by getting sentence embeddings from these models with proper pooling strategy. An encoder followed by a linear projection takes these embeddings as inputs and is trained under a contrastive objective. To evaluate the performance of CLSR, we run experiments on a range of pre-trained language models and their variants on a series of Semantic Contextual Similarity tasks. Results show that CLSR gains significant performance improvements over existing SOTA language models.


Extended Topic Model for Word Dependency
Tong Wang | Vish Viswanath | Ping Chen
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)


TreeMatch: A Fully Unsupervised WSD System Using Dependency Knowledge on a Specific Domain
Andrew Tran | Chris Bowes | David Brown | Ping Chen | Max Choly | Wei Ding
Proceedings of the 5th International Workshop on Semantic Evaluation


A Fully Unsupervised Word Sense Disambiguation Method Using Dependency Knowledge
Ping Chen | Wei Ding | Chris Bowes | David Brown
Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics