No abstract available.
Proceeding Downloads
Offensive Text Classification based on Ernie??s Dual Channel Composite Model
With the widespread popularity of the Internet, offensive text information in cyberspace has attracted widespread attention from society. Currently, offensive text recognition mainly relies on pre constructed sensitive words for recognition, which ...
Fake news detection algorithm based on incorporating multi-level features
With the development of social media, false news has become a serious problem facing today’s society. In view of the fact that most of the existing research on fake news detection technology relies on external knowledge sources, and there are still ...
Trademark Detection Based on Improved SSD Algorithm
Abstract: Trademarks are found everywhere in daily life. With the development of deep learning in the field of image recognition, trademark detection has become a hot research topic. Although trademark detection has made great progress, there are still ...
R-TES: Regularized Template Style for Generative Joint Relational Triple Extraction
Joint Relational Triple Extraction (RTE) is an important task in the field of information extraction. With the development of the pre-trained language models, the sequence-to-sequence (seq2seq) approaches have become one of the promising methods for ...
EEGCN: Event Evolutionary Graph Comparison Network for Multi-Modal Fake News Detection
In the contemporary landscape characterized by the pervasive use of social media, the proliferation of counterfeit news has become conspicuous. Consequently, the precise identification of such disinformation has assumed paramount significance. However, ...
Explainable Similar Legal Cases Retrieval Based on Siamese Network
Legal case retrieval is crucial for ensuring justice across different legal systems and has attracted increasing attention. However, most of the existing methods for legal case retrieval are based on frequency-based matching of words or encoding the ...
Robust Sentiment Classification Based on the Backdoor Adjustment
Deep NLP models are correlation-based learning, which has a critical limitation of over-fitting over spurious features and shows poor generalization capability in the out-of-distribution (OOD) setting. Existing methods encourage the model to exploit ...
Prior Knowledge Augmentation Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis is a popular task in Natural Language Processing (NLP). Many methods utilize attention mechanisms and graph neural networks on dependency trees to identify the most relevant opinion words for aspects. However, ...
A Multi-dimension and Multi-granularity Feature Fusion Method for Chinese Microblog Sentiment Classification
Chinese microblog comments exhibit a wide range of expressions, including brief terms and internet slang. Traditional single-feature models may not capturing this diversity comprehensively and in effectively discerning the usage of sentiment words, ...
Optimization Study on Weapon-Target Assignment in Problem Based on Intuitionistic Fuzzy Marine Predator Algorithm
Marine predator algorithm (MPA) is a nature-inspired metaheuristic proposed by simulating the moving strategies of marine predators and preys. To improve the solving speed and precision of weapon target assignment problems, a novel MPA solving strategy ...
Ensuring Ethical, Transparent, and Auditable Use of Education Data and Algorithms on AutoML
Automated machine learning (AutoML) creates additional opportunities for less advanced users to build and test their own data mining models. Even though AutoML creates the models for the user, there is still technical knowledge and tools needed to ...
A Novel Ranking Method for Textual Adversarial Attack
Adversarial examples highlight the potential weaknesses in text classifiers, and can be used to improve the robustness of classifiers. Previous attack models which use pre-trained language models to generate context-aware adversarial examples typically ...
A Person-job Matching Method Based on BM25 and Pre-trained Language Model
To address the inefficiency of traditional methods for person-job matching and the lack of interpretability of deep learning approaches, a novel approach for person-job matching based on BM25 and pre-trained language models is proposed. First, the BM25 ...
Reinforcement Learning in Natural Language Processing: A Survey
Reinforcement learning (RL) is a powerful technique for learning from data and feedback, but its effective application to natural language processing (NLP) tasks remains an open question. Consequently, this paper first introduces the general concepts of ...
An Application of Co-plot Analysis: A Multidimensional Scaling Data Visualization
Exploratory graphs are a crucial element of statistical analysis and models that help us identify and interpret data patterns. As one example of exploratory graphs, multidimensional scaling (MDS) allows the visualization of large and complex datasets in ...
Cancer Survival Prediction by Multimodal Disentangled Representation Learning
Precise prediction of cancer survival is of paramount importance in aiding clinicians in formulating tailored treatment strategies. Such strategies have the potential to enhance the quality of life for individuals with cancer and lower the mortality ...
Interpretable Recommendation Based on Review Aspect-Level Preferences
Review-based recommendation systems usually employ explicit independent methods to learn vector representations of users and items to enhance recommendation performance, while often disregarding the interpretability of the recommendations. This paper ...
Multi-view Representation Learning for Histologic Subtype Classification of Lung Cancer
It is crucial to accurately discerning adenocarcinoma (ADC) from squamous cell carcinoma (SCC) histological subtypes utilizing computed tomography (CT) scans for guiding treatment decisions among individuals with non-small cell lung cancer (NSCLC). While ...
Unsupervised Feature Selection for Multivariate Time Series based on Improved FINCH
Feature selection is a crucial step in the preprocessing of data mining for multivariate time series. In order to remove irrelevant and redundant features in the multivariate time series, an unsupervised feature selection method based on improved First ...
Multivariate Time Series Co-evolution Shapelet Learning Method
Shapelets are discriminative subsequences in time series that effectively capture local shape characteristics. However, the time complexity of the existing shapelet extraction process remains high. To address this issue, this paper proposes an ...
MDVT: A Multi-modal Fake News Detection Framework based on Vision Transformer
The growth of social media in recent years has contributed to the spread of fake news on the Internet. Since multimodal contents such as pictures have a huge impact on the spread of news in social media, researchers are increasingly focusing on the ...
Research on Tibetan-Chinese Neural Machine Translation Integrating Statistical Method
In recent years, with the emergence of deep learning methods, Neural Machine Translation has become a new research direction of machine translation. Due to the scarcity of digital resources in Tibetan, there is only a small-scale Tibetan-Chinese ...
CAPPST:Chinese AMR Parsing with Parameter-efficient Fine-tuned Pre-trained Language Model for Particular Sentence Types
As a semantic representation, Abstract Meaning Representation (AMR) is closely related to grammar. CAMR parsing, a Chinese sentences parsing task, aims to extract the core semantics of sentences from syntactic facts. Parameter-Efficient Fine-Tuning (...
Clustering Social Media Data for Bitcoin Price Prediction with Transformer Model
This paper explores the integration of social media data and natural language processing methods, specifically utilizing the Transformer model, to predict Bitcoin price movements. We aim to evaluate the effectiveness of using social media data and the ...
"Study on the Grammatical Function of \"la dhon\"as Function Words in the Tibetan Language Processing"
The study of Tibetan function words is an indispensable basic work in Tibetan natural language processing and has a wide range of practical application value. It is the core of Tibetan information processing and the basis of Tibetan natural language ...
Comparisons Among the Preliminary Test Kibria-Lukman Estimator Based on Three Large Sample Tests in the Linear Regression Model
The Preliminary Test Kibria-Lukman Estimator (PTKLE), which is based on the Wald (W), Likelihood Ratio (LR), and Lagrangian Multiplier (LM) tests, is offered in this study when it is believed that the regression parameter may be restricted to a ...
A Pedestrian Attribute Recognition Method Based On Cross-modal Fusion
Pedestrian Attribute Recognition (PAR), propelled by advancements in computer vision and deep learning, involves predicting attributes to describe pedestrians, including gender, age, clothing, and posture. Recent research has unveiled the oversight of ...
Experimental design of emotion recognition based on machine learning
In this paper, a wrist bracelet was used to measure the subjects' heart rate signals and skin electrical signals, and three types of emotions (positive, neutral and negative) were induced by designing an experimental environment. The heart rate and skin ...
Entity relation extraction based on Biaffine model with embedded context features
The extraction of entities and relationships from unstructured text is not only a critical issue in information extraction, but also an essential component of constructing knowledge graphs. Most existing models for relation extraction first extract all ...
GPT Rotational Position Embedding for Length Extrapolation
Since the introduction of the GPT model as the mainstream model for dialog generation, a hot issue is how to enable the model to extend the prediction length and generate longer dialog texts while the training context length remains constant. Rotary ...
Index Terms
- Proceedings of the 2023 6th International Conference on Machine Learning and Natural Language Processing