75 citations · 473 across the 72 of their papers we have counts for
74 papers
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Zhenwen Liang, Dian Yu, Xiaoman Pan +4
Reasoning in mathematical domains remains a significant challenge for relatively small language models (LMs). Many current methods focus on specializing LMs in mathematical reasoni…
Improving the Robustness of Summarization Systems with Dual Augmentation
Xiuying Chen, Guodong Long, Chongyang Tao +4
A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the…
A Topic-aware Summarization Framework with Different Modal Side Information
Xiuying Chen, Mingzhe Li, Shen Gao +5
Automatic summarization plays an important role in the exponential document growth on the Web. On content websites such as CNN.com and WikiHow.com, there often exist various kinds…
Learning towards Selective Data Augmentation for Dialogue Generation
Xiuying Chen, Mingzhe Li, Jiayi Zhang +6
As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples…
Knowledge Distillation on Graphs: A Survey
Yijun Tian, Shichao Pei, Xiangliang Zhang +2
Graph Neural Networks (GNNs) have attracted tremendous attention by demonstrating their capability to handle graph data. However, they are difficult to be deployed in resource-limi…
Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order
Xiuying Chen, Mingzhe Li, Shen Gao +5
Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution t…
AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs
Helene Orsini, Hongyan Bao, Yujun Zhou +6
Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns. Des…
Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputs
Hongyan Bao, Yufei Han, Yujun Zhou +2
Our work targets at searching feasible adversarial perturbation to attack a classifier with high-dimensional categorical inputs in a domain-agnostic setting. This is intrinsically…
Scientific Paper Extractive Summarization Enhanced by Citation Graphs
Xiuying Chen, Mingzhe Li, Shen Gao +3
In a citation graph, adjacent paper nodes share related scientific terms and topics. The graph thus conveys unique structure information of document-level relatedness that can be u…
Analogical Math Word Problems Solving with Enhanced Problem-Solution Association
Zhenwen Liang, Jipeng Zhang, Xiangliang Zhang
Math word problem (MWP) solving is an important task in question answering which requires human-like reasoning ability. Analogical reasoning has long been used in mathematical educ…
Generalizing Math Word Problem Solvers via Solution Diversification
Zhenwen Liang, Jipeng Zhang, Lei Wang +3
Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution s…
Towards Improving Faithfulness in Abstractive Summarization
Xiuying Chen, Mingzhe Li, Xin Gao +1
Despite the success achieved in neural abstractive summarization based on pre-trained language models, one unresolved issue is that the generated summaries are not always faithful…
NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs
Yijun Tian, Chuxu Zhang, Zhichun Guo +2
While Graph Neural Networks (GNNs) have demonstrated their efficacy in dealing with non-Euclidean structural data, they are difficult to be deployed in real applications due to the…
Few-shot News Recommendation via Cross-lingual Transfer
Taicheng Guo, Lu Yu, Basem Shihada +1
The cold-start problem has been commonly recognized in recommendation systems and studied by following a general idea to leverage the abundant interaction records of warm users to…
Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
Zhenwei Tang, Shichao Pei, Zhao Zhang +4
Most real-world knowledge graphs (KG) are far from complete and comprehensive. This problem has motivated efforts in predicting the most plausible missing facts to complete a given…
Target-aware Abstractive Related Work Generation with Contrastive Learning
Xiuying Chen, Hind Alamro, Mingzhe Li +4
The related work section is an important component of a scientific paper, which highlights the contribution of the target paper in the context of the reference papers. Authors can…
TAR: Neural Logical Reasoning across TBox and ABox
Zhenwei Tang, Shichao Pei, Xi Peng +3
Many ontologies, i.e., Description Logic (DL) knowledge bases, have been developed to provide rich knowledge about various domains. An ontology consists of an ABox, i.e., assertion…
Few-Shot Learning on Graphs
Chuxu Zhang, Kaize Ding, Jundong Li +4
Graph representation learning has attracted tremendous attention due to its remarkable performance in many real-world applications. However, prevailing supervised graph representat…
Data-Driven State Estimation for Light-Emitting Diode Underwater Optical Communication
Yingquan Li, Zhenwen Liang, Ibrahima N'Doye +3
Light-Emitting Diodes (LEDs) based underwater optical wireless communications (UOWCs), a technology with low latency and high data rates, have attracted significant importance for…
Meta Cross-Modal Hashing on Long-Tailed Data
Runmin Wang, Guoxian Yu, Carlotta Domeniconi +1
Due to the advantage of reducing storage while speeding up query time on big heterogeneous data, cross-modal hashing has been extensively studied for approximate nearest neighbor s…
Cross-modal Zero-shot Hashing by Label Attributes Embedding
Runmin Wang, Guoxian Yu, Lei Liu +3
Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search. Most CMH solutions ideally assume the labels of training and test…
Open-Set Crowdsourcing using Multiple-Source Transfer Learning
Guangyang Han, Guoxian Yu, Lei Liu +3
We raise and define a new crowdsourcing scenario, open set crowdsourcing, where we only know the general theme of an unfamiliar crowdsourcing project, and we don't know its label s…
Crowdsourcing with Meta-Workers: A New Way to Save the Budget
Guangyang Han, Guoxian Yu, Lizhen Cui +2
Due to the unreliability of Internet workers, it's difficult to complete a crowdsourcing project satisfactorily, especially when the tasks are multiple and the budget is limited. R…
Overview of the Arabic Sentiment Analysis 2021 Competition at KAUST
Hind Alamro, Manal Alshehri, Basma Alharbi +4
This paper provides an overview of the Arabic Sentiment Analysis Challenge organized by King Abdullah University of Science and Technology (KAUST). The task in this challenge is to…