A5031911989- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Advanced Text Analysis Techniques
- Text and Document Classification Technologies
- Natural Language Processing Techniques
- Higher Education and Teaching Methods
- Recommender Systems and Techniques
- Biochemical effects in animals
- Multimodal Machine Learning Applications
- Metabolism and Genetic Disorders
- Domain Adaptation and Few-Shot Learning
- Mental Health via Writing
- Emotion and Mood Recognition
- Geomagnetism and Paleomagnetism Studies
- Expert finding and Q&A systems
- Food Quality and Safety Studies
- Plant Genetic and Mutation Studies
- Machine Learning in Healthcare
- Natural Antidiabetic Agents Studies
- Plant tissue culture and regeneration
- Prenatal Screening and Diagnostics
- Ideological and Political Education
- Advanced Graph Neural Networks
- Complex Network Analysis Techniques
- Image Processing and 3D Reconstruction
Harbin Institute of Technology
2015-2024
Heilongjiang Institute of Technology
2011-2023
China Medical University
2006-2022
China Agricultural University
2022
Institute of Information Engineering
2021
Chinese Academy of Sciences
2021
University of Chinese Academy of Sciences
2021
Hainan University
2020
Chinese Academy of Medical Sciences & Peking Union Medical College
2016
Shandong University of Traditional Chinese Medicine
2016
Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeniy Kotelnikov, Nuria Bel, Salud María Jiménez-Zafra, Gülşen Eryiğit. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). 2016.
Sentiment analysis, which addresses the computational treatment of opinion, sentiment, and subjectivity in text, has received considerable attention recent years. In contrast to traditional coarse-grained sentiment analysis tasks, such as document-level classification, we are interested fine-grained aspect-based that aims identify aspects users comment on these aspects' polarities. Aspect-based relies heavily syntactic features. However, reviews this task focuses natural spontaneous, thus...
Multimodal fusion is a core problem for multimodal sentiment analysis.Previous works usually treat all three modal features equally and implicitly explore the interactions between different modalities.In this paper, we break kind of methods in two ways.Firstly, observe that textual modality plays most important role analysis, can be seen from previous works.Secondly, comparing to modality, other kinds nontextual modalities (visual acoustic) provide semantics, shared private semantics.The...
Emotion Recognition in Conversations has attained increasing interest the natural language processing community. Many neural-network based approaches endeavor to solve challenge of emotional dynamics conversations and gain appealing results. However, these works are limited capturing deep clues conversational context because they ignore emotion cause that could be viewed as stimulus target emotion. In this work, we propose Causal Aware Interaction Network (CauAIN) thoroughly understand with...
<h3>Background</h3> Lipid-storage myopathy (LSM), defined by triglyceride accumulation in muscle fibres, is a heterogeneous group of lipid metabolic disorders predominantly affecting skeletal muscle. In the past 15 years, more than 200 cases LSM have been reported Chinese literature, but accurate pathogenic mechanisms are still unknown. <h3>Objective</h3> order to gain insight into and genetic dysfunctions LSM, authors described patients with who were very responsive isolated riboflavin...
Sarcasm is a sophisticated linguistic phenomenon and commonly manifests on social media platforms, which poses great challenge for opinion mining systems. Therefore, multimodal sarcasm detection, aims to understand the implied sentiment in video, has gained more attention. However, previous works mostly focus feature fusion without explicitly modeling incongruity between modalities, such as expressing verbal compliments while rolling eyes, an obvious cue detecting sarcasm. In this article,...
Nowadays, adolescents would like to share their daily lives via social media platforms, which presents an excellent opportunity for us leverage these data develop techniques measure mental health status, such as depression. Previous researches focus on the more accurate detection of depression through statistical learning and ignore psychological understanding However, psychologists have given lots theoretical evidence Such according cognitive psychology research, distortions will result in...
Emotion recognition in conversations (ERC) has received much attention recently the natural language processing community. Considering that emotions of utterances are interactive, previous works usually implicitly model emotion interaction between by modeling dialogue context, but misleading information from context often interferes with interaction. We noticed gold labels can provide explicit and accurate interaction, it is impossible to input at inference time. To address this problem, we...
Writing comments on products or news has become a popular activity in social media. The amount of opinionated text available online been growing rapidly, increasing the need for techniques that can analyze opinions expressed such so reviews be easily absorbed by users. To date, most depend annotated corpora. However, existing corpora are almost sentence-level works ignore important global sentiment information other sentences. Given rise advanced applications, more fine-grained needed, even...
Emotion and sentiment play a central role in various human activities, such as perception, decision-making, social interaction, logical reasoning. Developing artificial emotional intelligence (AEI) for machines is becoming bottleneck human–computer interaction. The first step of AEI to recognize the emotion that are conveyed different affective signals. Traditional supervised analysis (ESA) methods, especially deep learning-based ones, usually require large-scale labeled training data....
In recent years, recommendation systems have attracted more and attention due to the rapid development of e-commerce. Reviews information can offer help in modeling user's preference item's performance. Some existing methods utilize reviews for recommendation. However, few those models consider importance words corpus together. Therefore, we propose an approach rating prediction using a hierarchical attention-based network named HANN, which distinguish at both word level review explanations...
Deep neural networks have been applied to learn transferable features for adapting text classification models from a source domain target domain. Conventional adaptation used adapt an individual specific with sufficient labeled data another without any (or little) data. However, in this paradigm, we lose sight of correlation among different domains where common knowledge could be shared improve the performance both and Multi-domain learning proposes sharable multiple previous work mainly...
Sequential recommendation systems alleviate the problem of information overload, and have attracted increasing attention in literature. Most prior works usually obtain an overall representation based on user's behavior sequence, which can not sufficiently reflect multiple interests user. To this end, we propose a novel method called PIMI to mitigate issue. model multi-interest effectively by considering both periodicity interactivity item sequence. Specifically, design periodicity-aware...
In this paper, we evaluate different abilities of GPT-4V including visual understanding, language puzzle solving, and understanding other modalities such as depth, thermal, video, audio. To estimate GPT-4V's performance, manually construct 656 test instances carefully the results GPT-4V. The highlights our findings are follows: (1) exhibits impressive performance on English visual-centric benchmarks but fails to recognize simple Chinese texts in images; (2) shows inconsistent refusal...
An appraisal expression is described as a collocation of the polarity word and its modified target, which can be considered an atomic unit expressing evaluative stance towards target. Recognizing expressions essential for sentence sentiment classification. However, relevant research far from enough. This paper proposes novel method that uses syntactic paths to recognize expressions. Compared with previous work, proposed path based has two advantages: 1) it automatically explores knowledge,...