171 citations · 280 across the 16 of their papers we have counts for
16 papers
A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches
Zihan Wang, Tianle Wang, Dheeraj Mekala +1
Etremely Weakly Supervised Text Classification (XWS-TC) refers to text classification based on minimal high-level human guidance, such as a few label-indicative seed words or class…
ClusterLLM: Large Language Models as a Guide for Text Clustering
Yuwei Zhang, Zihan Wang, Jingbo Shang
We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupe…
Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification
Chengyu Dong, Zihan Wang, Jingbo Shang
Recent advances in weakly supervised text classification mostly focus on designing sophisticated methods to turn high-level human heuristics into quality pseudo-labels. In this pap…
Goal-Driven Explainable Clustering via Language Descriptions
Zihan Wang, Jingbo Shang, Ruiqi Zhong
Unsupervised clustering is widely used to explore large corpora, but existing formulations neither consider the users' goals nor explain clusters' meanings. We propose a new task f…
WOT-Class: Weakly Supervised Open-world Text Classification
Tianle Wang, Zihan Wang, Weitang Liu +1
State-of-the-art weakly supervised text classification methods, while significantly reduced the required human supervision, still requires the supervision to cover all the classes…
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
Yufan Zhuang, Zihan Wang, Fangbo Tao +1
Transformer and its variants are fundamental neural architectures in deep learning. Recent works show that learning attention in the Fourier space can improve the long sequence lea…
WeDef: Weakly Supervised Backdoor Defense for Text Classification
Lesheng Jin, Zihan Wang, Jingbo Shang
Existing backdoor defense methods are only effective for limited trigger types. To defend different trigger types at once, we start from the class-irrelevant nature of the poisonin…
Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition
Zihan Wang, Kewen Zhao, Zilong Wang +1
Fine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks. We argue that under the few-shot…
UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
Xiaotao Gu, Zihan Wang, Zhenyu Bi +4
Identifying and understanding quality phrases from context is a fundamental task in text mining. The most challenging part of this task arguably lies in uncommon, emerging, and dom…
"Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language Models
Zihan Wang, Chengyu Dong, Jingbo Shang
Contextualized representations based on neural language models have furthered the state of the art in various NLP tasks. Despite its great success, the nature of such representatio…
X-Class: Text Classification with Extremely Weak Supervision
Zihan Wang, Dheeraj Mekala, Jingbo Shang
In this paper, we explore text classification with extremely weak supervision, i.e., only relying on the surface text of class names. This is a more challenging setting than the se…
Extending Multilingual BERT to Low-Resource Languages
Zihan Wang, Karthikeyan K, Stephen Mayhew +1
Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. However, this success has focused only on the top 104 languages…
Cross-Lingual Ability of Multilingual BERT: An Empirical Study
Karthikeyan K, Zihan Wang, Stephen Mayhew +1
Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no ali…
CrossWeigh: Training Named Entity Tagger from Imperfect Annotations
Zihan Wang, Jingbo Shang, Liyuan Liu +3
Everyone makes mistakes. So do human annotators when curating labels for named entity recognition (NER). Such label mistakes might hurt model training and interfere model compariso…
Raw-to-End Name Entity Recognition in Social Media
Liyuan Liu, Zihan Wang, Jingbo Shang +5
Taking word sequences as the input, typical named entity recognition (NER) models neglect errors from pre-processing (e.g., tokenization). However, these errors can influence the m…
Discriminative Topic Mining via Category-Name Guided Text Embedding
Yu Meng, Jiaxin Huang, Guangyuan Wang +4
Mining a set of meaningful and distinctive topics automatically from massive text corpora has broad applications. Existing topic models, however, typically work in a purely unsuper…