Baolin Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Baolin Peng has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jianfeng Gao
Microsoft Research Redmond
4 shared publications - Jinchao Li
School of Economics and Management, North China Electric Power University, Beijing 102206, China
2 shared publications Chunyuan Li
Microsoft Research Redmond
1 shared publication- Hui-Min Wang
Interventional Oncology, Johnson & Johnson Enterprise Innovation, Inc., Boston, Massachusetts
1 shared publication - Julia Kiseleva
Microsoft Research
1 shared publication - Kam-Fai Wong
The Chinese University of Hong Kong
1 shared publication
Latest Publications
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 18 (4) , 1-27
OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience
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
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 18 (4) , 1-27
Open AccessOPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience
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
- Open Access
Self-supervised Pre-training with Hard Examples Improves Visual Representations
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.
Open AccessSelf-supervised Pre-training with Hard Examples Improves Visual Representations
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.
- Open Access
Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
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.
Open AccessIs Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
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.
- Open Access
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 2308-2317
Guided Dialogue Policy Learning without Adversarial Learning in the Loop
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.
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 2308-2317
Open AccessGuided Dialogue Policy Learning without Adversarial Learning in the Loop
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.
- Open Access
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 6355-6365
Learning Efficient Dialogue Policy from Demonstrations through Shaping
Huimin Wang, Baolin Peng, Kam-Fai Wong. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.
- 1 January 2020
- Published by Association for Computational Linguistics (ACL)
- p. 6355-6365
Open AccessLearning Efficient Dialogue Policy from Demonstrations through Shaping
Huimin Wang, Baolin Peng, Kam-Fai Wong. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.
- 1 July 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5 (21614393) , 1-8
An empirical analysis of different sparse penalties for autoencoder in unsupervised feature learning
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 July 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5 (21614393) , 1-8
An empirical analysis of different sparse penalties for autoencoder in unsupervised feature learning
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.