Houfeng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Houfeng Wang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jing Jin
Department of Gynecology Maternal and Child Health Hospital of Hubei Province Wuhan PR China
1 shared publication - Jinxiong Xia
Peking University, Beijing, China
1 shared publication - Li Li
University of Nevada Reno
1 shared publication - Li Li
Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China
1 shared publication - Linhao Zhang
School of Nuclear Science and Technology, University of Science and Technology of China, No. 443, Huangshan Road, Hefei 230027, P. R. China
1 shared publication - Linjun Shou
Microsoft Edge Consumer
1 shared publication
Latest Publications
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2683-2693
A Sequence-to-Sequence Approach with Mixed Pointers to Topic Segmentation and Segment Labeling
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2683-2693
Open AccessA Sequence-to-Sequence Approach with Mixed Pointers to Topic Segmentation and Segment Labeling
- Open Access
Using calibrator to improve robustness in Machine Reading Comprehension
Machine Reading Comprehension(MRC) has achieved a remarkable result since some powerful models, such as BERT, are proposed. However, these models are not robust enough and vulnerable to adversarial input perturbation and generalization examples. Some works tried to improve the performance on specific types of data by adding some related examples into training data while it leads to degradation on the original dataset, because the shift of data distribution makes the answer ranking based on the softmax probability of model unreliable. In this paper, we propose a method to improve the robustness by using a calibrator as the post-hoc reranker, which is implemented based on XGBoost model. The calibrator combines both manual features and representation learning features to rerank candidate results. Experimental results on adversarial datasets show that our model can achieve performance improvement by more than 10\% and also make improvement on the original and generalization datasets.
Open AccessUsing calibrator to improve robustness in Machine Reading Comprehension
Machine Reading Comprehension(MRC) has achieved a remarkable result since some powerful models, such as BERT, are proposed. However, these models are not robust enough and vulnerable to adversarial input perturbation and generalization examples. Some works tried to improve the performance on specific types of data by adding some related examples into training data while it leads to degradation on the original dataset, because the shift of data distribution makes the answer ranking based on the softmax probability of model unreliable. In this paper, we propose a method to improve the robustness by using a calibrator as the post-hoc reranker, which is implemented based on XGBoost model. The calibrator combines both manual features and representation learning features to rerank candidate results. Experimental results on adversarial datasets show that our model can achieve performance improvement by more than 10\% and also make improvement on the original and generalization datasets.
- Open Access
A Joint and Domain-Adaptive Approach to Spoken Language Understanding
Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other focuses on the domain-adaptation ability of one of the subtasks. In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU. We formulate SLU as a constrained generation task and utilize a dynamic vocabulary based on domain-specific ontology. We conduct experiments on the ASMixed and MTOD datasets and achieve competitive performance with previous state-of-the-art joint models. Besides, results show that our joint model can be effectively adapted to a new domain.
Open AccessA Joint and Domain-Adaptive Approach to Spoken Language Understanding
Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other focuses on the domain-adaptation ability of one of the subtasks. In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU. We formulate SLU as a constrained generation task and utilize a dynamic vocabulary based on domain-specific ontology. We conduct experiments on the ASMixed and MTOD datasets and achieve competitive performance with previous state-of-the-art joint models. Besides, results show that our joint model can be effectively adapted to a new domain.
- Open Access
- 8 November 2015
- Published by Springer Nature
- p. 103-115
Negative Emotion Recognition in Spoken Dialogs
- 8 November 2015
- Published by Springer Nature
- p. 103-115
Open AccessNegative Emotion Recognition in Spoken Dialogs
- Open Access
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 1405-1414
Predicting Chinese Abbreviations with Minimum Semantic Unit and Global Constraints
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 1405-1414
Open AccessPredicting Chinese Abbreviations with Minimum Semantic Unit and Global Constraints