Baolin Peng

Baolin Peng

Auto-generated profile, based on publicly available information

Baolin Peng

Microsoft Research, Redmond, United States

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2015
Verified
Conference Paper
Closed access
NJNan Jiang
Nan Jiang
WRWenge Rong
Wenge Rong
BPBaolin Peng
Baolin Peng
YNYifan Nie
Yifan Nie
ZXZhang Xiong
Zhang Xiong
Machine learning algorithms depend heavily on the data representation, which dominates its success in experiment accuracy. Autoencoder model structure is proposed to learn from data a good representation with the least possible amount of distortion. Furthermore, it has been proven that boosting sparsity when learning representation can significantly improve performance on classification tasks and also make the feature vector easy to interpret. One straightforward approach for autoencoder to obtain sparse representation is to impose sparse penalty on its overall cost function. Nevertheless, few comparative analysis has been conducted to evaluate which sparse penalty term works better. In this paper, we adopt L1 norm, L2 norm, Student-t penalties, which are rarely deployed to penalise the hidden unit outputs, and commonly used penalty KL-divergence in the literature. Then, we present a detailed analysis to evaluate which penalty achieves better result in terms of reconstruction error, sparseness of representation and classification performance on test datasets. Experimental study on MNIST, CIFAR-10, SVHN, OPTDIGITS and NORB datasets reveals that all these penalties achieve sparse representation and outperforms representations learned by pure autoencoder on classification performance and sparseness of feature vectors. Moreover, we hope this topics and the practices would provide insights for future research.

1 January 2020
Verified
Conference Paper
Open access
PDF file
ZLZiming Li
Ziming Li
SLSungjin Lee
Sungjin Lee
BPBaolin Peng
Baolin Peng
JLJinchao Li
Jinchao Li
JKJulia Kiseleva
Julia Kiseleva
JGJianfeng Gao
Jianfeng Gao
Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li, Julia Kiseleva, Maarten de Rijke, Shahin Shayandeh, Jianfeng Gao. Findings of the Association for Computational Linguistics: EMNLP 2020. 2020.

8 October 2024 in ACM Transactions on the Web
Verified
Journal Article
Open access
MLMiaoran Li
Miaoran Li
BPBaolin Peng
Baolin Peng
JGJianfeng Gao
Jianfeng Gao
ZZZhu Zhang
Zhu Zhang
Existing studies in conversational AI mostly treat task-oriented dialog (TOD) and question answering (QA) as separate tasks. Towards the goal of constructing a conversational agent that can complete user tasks and support information seeking, it is important to develop a system that can handle both TOD and QA with access to various external knowledge sources. In this work, we propose a new task, Open-Book TOD (OB-TOD), which combines TOD with QA and expands the external knowledge sources to include both explicit sources (e.g., the web) and implicit sources (e.g., pre-trained language models). We create a new dataset OB-MultiWOZ, where we enrich TOD sessions with QA-like information-seeking experience grounded on external knowledge. We propose a unified model OPERA ( Op en-book E nd-to-end Task-o r iented Di a log) which can appropriately access explicit and implicit external knowledge to tackle the OB-TOD task. Experimental results show that OPERA outperforms closed-book baselines, highlighting the value of both types of knowledge. 1

1 January 2020
Verified
Conference Paper
Open access
PDF file
HWHuimin Wang
Huimin Wang
BPBaolin Peng
Baolin Peng
KWKam-Fai Wong
Kam-Fai Wong
Huimin Wang, Baolin Peng, Kam-Fai Wong. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

4 January 2021 in arXiv
Verified
Preprint
Open access
PDF file
CLChunyuan Li
Chunyuan Li
XLXiujun Li
Xiujun Li
LZLei Zhang
Lei Zhang
BPBaolin Peng
Baolin Peng
MZMingyuan Zhou
Mingyuan Zhou
JGJianfeng Gao
Jianfeng Gao
Self-supervised pre-training (SSP) employs random image transformations to generate training data for visual representation learning. In this paper, we first present a modeling framework that unifies existing SSP methods as learning to predict pseudo-labels. Then, we propose new data augmentation methods of generating training examples whose pseudo-labels are harder to predict than those generated via random image transformations. Specifically, we use adversarial training and CutMix to create hard examples (HEXA) to be used as augmented views for MoCo-v2 and DeepCluster-v2, leading to two variants HEXA_{MoCo} and HEXA_{DCluster}, respectively. In our experiments, we pre-train models on ImageNet and evaluate them on multiple public benchmarks. Our evaluation shows that the two new algorithm variants outperform their original counterparts, and achieve new state-of-the-art on a wide range of tasks where limited task supervision is available for fine-tuning. These results verify that hard examples are instrumental in improving the generalization of the pre-trained models.

15 May 2020 in arXiv
Verified
Preprint
Open access
PDF file
RTRyuichi Takanobu
Ryuichi Takanobu
QZQi Zhu
Qi Zhu
JLJinchao Li
Jinchao Li
BPBaolin Peng
Baolin Peng
JGJianfeng Gao
Jianfeng Gao
MHMinlie Huang
Minlie Huang
There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations. Although many methods are devised to evaluate and improve the performance of individual dialog components, there is a lack of comprehensive empirical study on how different components contribute to the overall performance of a dialog system. In this paper, we perform a system-wise evaluation and present an empirical analysis on different types of dialog systems which are composed of different modules in different settings. Our results show that (1) a pipeline dialog system trained using fine-grained supervision signals at different component levels often obtains better performance than the systems that use joint or end-to-end models trained on coarse-grained labels, (2) component-wise, single-turn evaluation results are not always consistent with the overall performance of a dialog system, and (3) despite the discrepancy between simulators and human users, simulated evaluation is still a valid alternative to the costly human evaluation especially in the early stage of development.