Houfeng Wang

Houfeng Wang

Auto-generated profile, based on publicly available information

Houfeng Wang

Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 January 2014
Verified
Conference Paper
Open access
LZLongkai Zhang
Longkai Zhang
LLLi Li
Li Li
HWHoufeng Wang
Houfeng Wang
XSXu Sun
Xu Sun


8 November 2015
Verified
Book Chapter
Open access
PDF file
XZXiaodong Zhang
Xiaodong Zhang
HWHoufeng Wang
Houfeng Wang
LLLi Li
Li Li
MZMaoxiang Zhao
Maoxiang Zhao
QLQuanzhong Li
Quanzhong Li
Increasing attention has been directed to the study of the automatic emotion recognition in human speech recently. This paper presents an approach for recognizing negative emotions in spoken dialogs at the utterance level. Our approach mainly includes two parts. First, in addition to the traditional acoustic features, linguistic features based on distributed representation are extracted from the text transcribed by an automatic speech recognition (ASR) system. Second, we propose a novel deep learning model, multi-feature stacked denoising autoencoders (MSDA), which can fuse the high-level representations of the acoustic and linguistic features along with contexts to classify emotions. Experimental results demonstrate that our proposed method yields an absolute improvement over the traditional method by 5.2 %.

25 July 2021 in arXiv
Verified
Preprint
Open access
PDF file
LZLinhao Zhang
Linhao Zhang
YSYu Shi
Yu Shi
LSLinjun Shou
Linjun Shou
MGMing Gong
Ming Gong
HWHoufeng Wang
Houfeng Wang
MZMichael Zeng
Michael Zeng
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.

24 February 2022 in arXiv
Verified
Preprint
Open access
PDF file
JJJing Jin
Jing Jin
HWHoufeng Wang
Houfeng Wang
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.