1 code implementation • 10 Apr 2022 • Yu Kang, Tianqiao Liu, Hang Li, Yang Hao, Wenbiao Ding
Our pre-training framework consists of the following components: (1) Intra-modal Denoising Auto-Encoding (IDAE), which is able to reconstruct input text (audio) representations from a noisy version of itself.
1 code implementation • NeurIPS 2021 • Zhenyu Huang, guocheng niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, Hua Wu, Xi Peng
Based on this observation, we reveal and study a latent and challenging direction in cross-modal matching, named noisy correspondence, which could be regarded as a new paradigm of noisy labels.
1 code implementation • EMNLP 2021 • Hang Li, Yu Kang, Tianqiao Liu, Wenbiao Ding, Zitao Liu
Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms.
1 code implementation • 15 Jul 2021 • Hang Li, Yu Kang, Yang Hao, Wenbiao Ding, Zhongqin Wu, Zitao Liu
The quality of vocal delivery is one of the key indicators for evaluating teacher enthusiasm, which has been widely accepted to be connected to the overall course qualities.
1 code implementation • 15 Jul 2021 • Shiting Xu, Guowei Xu, Peilei Jia, Wenbiao Ding, Zhongqin Wu, Zitao Liu
A TR writing question may include multiple requirements and a high-quality essay must respond to each requirement thoroughly and accurately.
1 code implementation • ACL (RepL4NLP) 2021 • Yang Hao, Xiao Zhai, Wenbiao Ding, Zitao Liu
A challenging aspect of this problem is that the quality of crowdsourced labels suffer high intra- and inter-observer variability.
no code implementations • 15 Jul 2021 • Jiahao Chen, Hang Li, Wenbiao Ding, Zitao Liu
In this paper, we propose a simple yet effective solution to build practical teacher recommender systems for online one-on-one classes.
1 code implementation • 15 Jul 2021 • Guowei Xu, Wenbiao Ding, Weiping Fu, Zhongqin Wu, Zitao Liu
Despite that pre-trained models achieve state-of-the-art performance in many NLP benchmarks, we prove that they are not robust to noisy texts generated by real OCR engines.
Optical Character Recognition Optical Character Recognition (OCR) +2
1 code implementation • 15 Jul 2021 • Yang Hao, Hang Li, Wenbiao Ding, Zhongqin Wu, Jiliang Tang, Rose Luckin, Zitao Liu
In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective study habits.
1 code implementation • 15 Jul 2021 • Qiongqiong Liu, Tianqiao Liu, Jiafu Zhao, Qiang Fang, Wenbiao Ding, Zhongqin Wu, Feng Xia, Jiliang Tang, Zitao Liu
Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options.
no code implementations • 9 Jun 2021 • Han Xu, Xiaorui Liu, Wentao Wang, Wenbiao Ding, Zhongqin Wu, Zitao Liu, Anil Jain, Jiliang Tang
In this work, we study the effect of memorization in adversarial trained DNNs and disclose two important findings: (a) Memorizing atypical samples is only effective to improve DNN's accuracy on clean atypical samples, but hardly improve their adversarial robustness and (b) Memorizing certain atypical samples will even hurt the DNN's performance on typical samples.
1 code implementation • ACL 2021 • Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang
Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation.
1 code implementation • ACL 2021 • Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang
Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation.
1 code implementation • EMNLP 2021 • Tianqiao Liu, Qiang Fang, Wenbiao Ding, Hang Li, Zhongqin Wu, Zitao Liu
There is an increasing interest in the use of mathematical word problem (MWP) generation in educational assessment.
1 code implementation • 23 Sep 2020 • Wentao Wang, Guowei Xu, Wenbiao Ding, Gale Yan Huang, Guoliang Li, Jiliang Tang, Zitao Liu
Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines.
no code implementations • 16 May 2020 • Shiting Xu, Wenbiao Ding, Zitao Liu
Online one-on-one class is created for highly interactive and immersive learning experience.
no code implementations • 16 May 2020 • Gale Yan Huang, Jiahao Chen, Haochen Liu, Weiping Fu, Wenbiao Ding, Jiliang Tang, Songfan Yang, Guoliang Li, Zitao Liu
Asking questions is one of the most crucial pedagogical techniques used by teachers in class.
no code implementations • 15 May 2020 • Hang Li, Zhiwei Wang, Jiliang Tang, Wenbiao Ding, Zitao Liu
Classroom activity detection (CAD) aims at accurately recognizing speaker roles (either teacher or student) in classrooms.
2 code implementations • 21 Mar 2020 • Yang Hao, Wenbiao Ding, Zitao Liu
Representation learning approaches require a massive amount of discriminative training data, which is unavailable in many scenarios, such as healthcare, smart city, education, etc.
no code implementations • 21 Mar 2020 • Hang Li, Wenbiao Ding, Zitao Liu
We conduct a wide range of offline and online experiments to demonstrate the effectiveness of our approach.
no code implementations • 22 Oct 2019 • Hang Li, Yu Kang, Wenbiao Ding, Song Yang, Songfan Yang, Gale Yan Huang, Zitao Liu
The experimental results demonstrate the benefits of our approach on learning attention based neural network from classroom data with different modalities, and show our approach is able to outperform state-of-the-art baselines in terms of various evaluation metrics.
no code implementations • 23 Sep 2019 • Tiaoqiao Liu, Wenbiao Ding, Zhiwei Wang, Jiliang Tang, Gale Yan Huang, Zitao Liu
Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads.
no code implementations • 1 Sep 2019 • Jiahao Chen, Hang Li, Wenxin Wang, Wenbiao Ding, Gale Yan Huang, Zitao Liu
To warn the unqualified instructors and ensure the overall education quality, we build a monitoring and alerting system by utilizing multimodal information from the online environment.
no code implementations • 1 Aug 2019 • Wenbiao Ding, Guowei Xu, Tianqiao Liu, Weiping Fu, Yujia Song, Chaoyou Guo, Cong Kong, Songfan Yang, Gale Yan Huang, Zitao Liu
In our offline experiments, we show that Dolphin improves both phonological fluency and semantic relevance evaluation performance when compared to state-of-the-art baselines on real-world educational data sets.
1 code implementation • 18 Jul 2019 • Guowei Xu, Wenbiao Ding, Jiliang Tang, Songfan Yang, Gale Yan Huang, Zitao Liu
In practice, the crowdsourced labels are usually inconsistent among crowd workers given their diverse expertise and the number of crowdsourced labels is very limited.