Search Results for author: Yichong Xu

Found 24 papers, 7 papers with code

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention

no code implementations6 Dec 2021 Yichong Xu, Chenguang Zhu, Shuohang Wang, Siqi Sun, Hao Cheng, Xiaodong Liu, Jianfeng Gao, Pengcheng He, Michael Zeng, Xuedong Huang

In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities.

Leveraging Knowledge in Multilingual Commonsense Reasoning

no code implementations16 Oct 2021 Yuwei Fang, Shuohang Wang, Yichong Xu, Ruochen Xu, Siqi Sun, Chenguang Zhu, Michael Zeng

Then we utilize a diverse of 4 English knowledge sources to provide more comprehensive coverage of knowledge in different formats.

Language Modelling Translation

Dict-BERT: Enhancing Language Model Pre-training with Dictionary

no code implementations13 Oct 2021 Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang

In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary.

Language Modelling

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

no code implementations8 Oct 2021 Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng

The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module.

Open-Domain Question Answering Passage Retrieval

DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization

1 code implementation6 Sep 2021 Ming Zhong, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng

For a dialogue, it corrupts a window of text with dialogue-inspired noise, and guides the model to reconstruct this window based on the content of the remaining conversation.

Denoising Dialogue Understanding +1

Retrieval Enhanced Model for Commonsense Generation

1 code implementation Findings (ACL) 2021 Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts.

Text Generation

Fusing Context Into Knowledge Graph for Commonsense Question Answering

1 code implementation Findings (ACL) 2021 Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, Xuedong Huang

However, although a KG contains rich structural information, it lacks the context to provide a more precise understanding of the concepts.

Knowledge Graphs Language Modelling +2

Preference-based Reinforcement Learning with Finite-Time Guarantees

no code implementations NeurIPS 2020 Yichong Xu, Ruosong Wang, Lin F. Yang, Aarti Singh, Artur Dubrawski

If preferences are stochastic, and the preference probability relates to the hidden reward values, we present algorithms for PbRL, both with and without a simulator, that are able to identify the best policy up to accuracy $\varepsilon$ with high probability.

Zeroth Order Non-convex optimization with Dueling-Choice Bandits

no code implementations3 Nov 2019 Yichong Xu, Aparna Joshi, Aarti Singh, Artur Dubrawski

We consider a novel setting of zeroth order non-convex optimization, where in addition to querying the function value at a given point, we can also duel two points and get the point with the larger function value.

Active Learning for Graph Neural Networks via Node Feature Propagation

no code implementations16 Oct 2019 Yuexin Wu, Yichong Xu, Aarti Singh, Yiming Yang, Artur Dubrawski

Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data.

Active Learning General Classification +1

Thresholding Bandit Problem with Both Duels and Pulls

no code implementations14 Oct 2019 Yichong Xu, Xi Chen, Aarti Singh, Artur Dubrawski

The Thresholding Bandit Problem (TBP) aims to find the set of arms with mean rewards greater than a given threshold.

Active Learning Graph Neural Networks via Node Feature Propagation

no code implementations25 Sep 2019 Yuexin Wu, Yichong Xu, Aarti Singh, Artur Dubrawski, Yiming Yang

Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data.

Active Learning Node Classification

Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension

5 code implementations NAACL 2019 Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, Jianfeng Gao

We propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains.

Machine Reading Comprehension Machine Translation +3

Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information

no code implementations ICML 2018 Yichong Xu, Hariank Muthakana, Sivaraman Balakrishnan, Aarti Singh, Artur Dubrawski

Finally, we present experiments that show the efficacy of RR and investigate its robustness to various sources of noise and model-misspecification.

On Strategyproof Conference Peer Review

1 code implementation16 Jun 2018 Yichong Xu, Han Zhao, Xiaofei Shi, Jeremy Zhang, Nihar B. Shah

We then empirically show that the requisite property on the authorship graph is indeed satisfied in the submission data from the ICLR conference, and further demonstrate a simple trick to make the partitioning method more practically appealing for conference peer review.

Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information

no code implementations ICML 2018 Yichong Xu, Sivaraman Balakrishnan, Aarti Singh, Artur Dubrawski

In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction.

Noise-Tolerant Interactive Learning Using Pairwise Comparisons

no code implementations NeurIPS 2017 Yichong Xu, Hongyang Zhang, Kyle Miller, Aarti Singh, Artur Dubrawski

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive.

Dynamic Fusion Networks for Machine Reading Comprehension

no code implementations14 Nov 2017 Yichong Xu, Jingjing Liu, Jianfeng Gao, Yelong Shen, Xiaodong Liu

This paper presents a novel neural model - Dynamic Fusion Network (DFN), for machine reading comprehension (MRC).

Machine Reading Comprehension

Noise-Tolerant Interactive Learning from Pairwise Comparisons

no code implementations19 Apr 2017 Yichong Xu, Hongyang Zhang, Aarti Singh, Kyle Miller, Artur Dubrawski

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive.

The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification

no code implementations CVPR 2015 Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, Zheng Zhang

Our pipeline integrates three types of attention: the bottom-up attention that propose candidate patches, the object-level top-down attention that selects relevant patches to a certain object, and the part-level top-down attention that localizes discriminative parts.

Fine-Grained Image Classification General Classification

Scale-Invariant Convolutional Neural Networks

no code implementations24 Nov 2014 Yichong Xu, Tianjun Xiao, Jiaxing Zhang, Kuiyuan Yang, Zheng Zhang

Even though convolutional neural networks (CNN) has achieved near-human performance in various computer vision tasks, its ability to tolerate scale variations is limited.

Data Augmentation General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.