Chengqing Zong

Prof. Dr. Chengqing Zong


Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
2 December 2016
Verified
Book Chapter
Closed access
PDF file
CDChuanhai Dong
Chuanhai Dong
JZJiajun Zhang
Jiajun Zhang
CZChengqing Zong
Chengqing Zong
MHMasanori Hattori
Masanori Hattori
HDHui Di
Hui Di

18 June 2018 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
HLHaoran Li
Haoran Li
JZJunnan Zhu
Junnan Zhu
CMCong Ma
Cong Ma
JZJiajun Zhang
Jiajun Zhang
CZChengqing Zong
Chengqing Zong
Automatic text summarization is a fundamental NLP application that aims to condense a source text into a shorter version. The rapid increase in multimedia data transmission over the Internet necessitates multi-modal summarization (MMS) from asynchronous collections of text, image, audio and video. In this work, we propose an extractive MMS method that unites the techniques of NLP, speech processing and computer vision to explore the rich information contained in multi-modal data and to improve the quality of MMS. The key idea is to bridge the semantic gaps between multi-modal content. For audio information, we design an approach to selectively use its transcription and to infer the salience of the transcription with audio signals. For visual information, we learn the joint representations of text and images using a neural network. Then, we capture the coverage of the generated summary for important visual information through text-image matching or multi-modal topic modeling. Finally, all the multi-modal aspects are considered to generate a textual summary by maximizing the salience, non-redundancy, readability and coverage through the budgeted optimization of submodular functions. We further introduce a publicly available MMS corpus in English and Chinese. The experimental results demonstrate that our methods outperform other competitive baseline methods.

2 June 2023 in Machine Intelligence Research
Verified
Journal Article
Closed access
PDF file
YZYang Zhao
Yang Zhao
JZJiajun Zhang
Jiajun Zhang
CZChengqing Zong
Chengqing Zong

1 February 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JSJingyuan Sun
Jingyuan Sun
SWShaonan Wang
Shaonan Wang
JZJiajun Zhang
Jiajun Zhang
CZChengqing Zong
Chengqing Zong
Building computational models to account for the cortical representation of language plays an important role in understanding the human linguistic system. Recent progress in distributed semantic models (DSMs), especially transformer-based methods, has driven advances in many language understanding tasks, making DSM a promising methodology to probe brain language processing. DSMs have been shown to reliably explain cortical responses to word stimuli. However, characterizing the brain activities for sentence processing is much less exhaustively explored with DSMs, especially the deep neural network-based methods. What is the relationship between cortical sentence representations against DSMs? What linguistic features that a DSM catches better explain its correlation with the brain activities aroused by sentence stimuli? Could distributed sentence representations help to reveal the semantic selectivity of different brain areas? We address these questions through the lens of neural encoding and decoding, fueled by the latest developments in natural language representation learning. We begin by evaluating the ability of a wide range of 12 DSMs to predict and decipher the functional magnetic resonance imaging (fMRI) images from humans reading sentences. Most models deliver high accuracy in the left middle temporal gyrus (LMTG) and left occipital complex (LOC). Notably, encoders trained with transformer-based DSMs consistently outperform other unsupervised structured models and all the unstructured baselines. With probing and ablation tasks, we further find that differences in the performance of the DSMs in modeling brain activities can be at least partially explained by the granularity of their semantic representations. We also illustrate the DSM's selectivity for concept categories and show that the topics are represented by spatially overlapping and distributed cortical patterns. Our results corroborate and extend previous findings in understanding the relation between DSMs and neural activation patterns and contribute to building solid brain-machine interfaces with deep neural network representations.

15 September 2020 in Science China Technological Sciences
Verified
Journal Article
Closed access
PDF file
JZJiaJun Zhang
JiaJun Zhang
CZChengqing Zong
Chengqing Zong

1 January 2008
Verified
Conference Paper
Open access
PDF file
SLShoushan Li
Shoushan Li
CZChengqing Zong
Chengqing Zong
This paper addresses a new task in sentiment classification, called multi-domain sentiment classification, that aims to improve performance through fusing training data from multiple domains. To achieve this, we propose two approaches of fusion, feature-level and classifier-level, to use training data from multiple domains simultaneously. Experimental studies show that multi-domain sentiment classification using the classifier-level approach performs much better than single domain classification (using the training data individually).