203 citations · 229 across the 13 of their papers we have counts for
13 papers
A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
Wanyun Cui
Linear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exact memory: when many key--val…
Evade ChatGPT Detectors via A Single Space
Shuyang Cai, Wanyun Cui
ChatGPT brings revolutionary social value but also raises concerns about the misuse of AI-generated text. Consequently, an important question is how to detect whether texts are gen…
Exploring Automatically Perturbed Natural Language Explanations in Relation Extraction
Wanyun Cui, Xingran Chen
Previous research has demonstrated that natural language explanations provide valuable inductive biases that guide models, thereby improving the generalization ability and data eff…
Free Lunch for Efficient Textual Commonsense Integration in Language Models
Wanyun Cui, Xingran Chen
Recent years have witnessed the emergence of textual commonsense knowledge bases, aimed at providing more nuanced and context-rich knowledge. The integration of external commonsens…
Instance-based Learning for Knowledge Base Completion
Wanyun Cui, Xingran Chen
In this paper, we propose a new method for knowledge base completion (KBC): instance-based learning (IBL). For example, to answer (Jill Biden, lived city,? ), instead of going dire…
Open Rule Induction
Wanyun Cui, Xingran Chen
Rules have a number of desirable properties. It is easy to understand, infer new knowledge, and communicate with other inference systems. One weakness of the previous rule inductio…
Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense
Wanyun Cui, Xingran Chen
We study how to enhance text representation via textual commonsense. We point out that commonsense has the nature of domain discrepancy. Namely, commonsense has different data form…
Isotonic Data Augmentation for Knowledge Distillation
Wanyun Cui, Sen Yan
Knowledge distillation uses both real hard labels and soft labels predicted by teacher models as supervision. Intuitively, we expect the soft labels and hard labels to be concordan…
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning
Wanyun Cui, Guangyu Zheng, Wei Wang
We propose to solve the natural language inference problem without any supervision from the inference labels via task-agnostic multimodal pretraining. Although recent studies of mu…
Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement
Zhiqiang Shen, Zhankui He, Wanyun Cui +4
Generic Image recognition is a fundamental and fairly important visual problem in computer vision. One of the major challenges of this task lies in the fact that single image usual…
KBQA: Learning Question Answering over QA Corpora and Knowledge Bases
Wanyun Cui, Yanghua Xiao, Haixun Wang +3
Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. Unlike web search, QA over a knowledge base gives out accurate and concise resu…
Transfer Learning for Sequences via Learning to Collocate
Wanyun Cui, Guangyu Zheng, Zhiqiang Shen +2
Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfe…
Verb Pattern: A Probabilistic Semantic Representation on Verbs
Wanyun Cui, Xiyou Zhou, Hangyu Lin +4
Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too…