Natural language processing and Chinese computing . Part II : 11th CCF International Conference, NLPCC 2022, Guilin, China, September 24-25, 2022, proceedings / / Wei Lu [and three others]

• Pubblicazione: Cham, Switzerland : , : Springer, , [2022]; ©2022
• Descrizione fisica: 1 online resource (385 pages)
• Disciplina: 495.10285
• Soggetto topico: Chinese language - Data processing; Natural language processing (Computer science)
• Persona (resp. second.): LuWei
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part II -- Contents - Part I -- Question Answering (Poster) -- Faster and Better Grammar-Based Text-to-SQL Parsing via Clause-Level Parallel Decoding and Alignment Loss -- 1 Introduction -- 2 Related Works -- 3 Our Proposed Model -- 3.1 Grammar-Based Text-to-SQL Parsing -- 3.2 Clause-Level Parallel Decoding -- 3.3 Clause-Level Alignment Loss -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Results -- 4.3 Analysis -- 5 Conclusions -- References -- Two-Stage Query Graph Selection for Knowledge Base Question Answering -- 1 Introduction -- 2 Our Approach -- 2.1 Query Graph Generation -- 2.2 Two-Stage Query Graph Selection -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Main Results -- 3.3 Discussion and Analysis -- 4 Related Work -- 5 Conclusions -- References -- Plug-and-Play Module for Commonsense Reasoning in Machine Reading Comprehension -- 1 Introduction -- 2 Methodology -- 2.1 Task Formulation -- 2.2 Proposed Module: PIECER -- 2.3 Plugging PIECER into MRC Models -- 3 Experiments -- 3.1 Datasets -- 3.2 Base Models -- 3.3 Experimental Settings -- 3.4 Main Results -- 3.5 Analysis and Discussions -- 4 Related Work -- 5 Conclusion -- References -- Social Media and Sentiment Analysis (Poster) -- FuDFEND: Fuzzy-Domain for Multi-domain Fake News Detection -- 1 Introduction -- 2 Related Work -- 2.1 Fake News Detection Methods -- 2.2 Multi-domain Rumor Task -- 3 FuDFEND: Fuzzy-Domain Fake News Detection Model -- 3.1 Membership Function -- 3.2 Feature Extraction -- 3.3 Domain Gate -- 3.4 Fake News Prediction and Loss Function -- 4 Experiment -- 4.1 Dataset -- 4.2 Experiment Setting -- 4.3 Train Membership Function and FuDFEND -- 4.4 Experiment on Weibo21 -- 4.5 Experiment on Thu Dataset -- 5 Conclusion -- 6 Future Work -- References -- NLP Applications and Text Mining (Poster). ; Continuous Prompt Enhanced Biomedical Entity Normalization -- 1 Introduction -- 2 Related Work -- 2.1 Biomedical Entity Normalization -- 2.2 Prompt Learning and Contrastive Loss -- 3 Our Method -- 3.1 Prompt Enhanced Scoring Mechanism -- 3.2 Contrastive Loss Enhanced Training Mechanism -- 4 Experiments and Analysis -- 4.1 Dataset and Evaluation -- 4.2 Data Preprocessing -- 4.3 Experiment Setting -- 4.4 Overall Performance -- 4.5 Ablation Study -- 5 Conclusion -- References -- Bidirectional Multi-channel Semantic Interaction Model of Labels and Texts for Text Classification -- 1 Introduction -- 2 Model -- 2.1 Preliminaries -- 2.2 Bidirectional Multi-channel Semantic Interaction Model -- 3 Experiments -- 3.1 Experimental Settings -- 3.2 Results and Analysis -- 3.3 Ablation Test -- 4 Conclusions -- References -- Exploiting Dynamic and Fine-grained Semantic Scope for Extreme Multi-label Text Classification -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Notation -- 3.2 TReaderXML -- 4 Experiments -- 4.1 Datasets and Preprocessing -- 4.2 Baselines -- 4.3 Evaluation Metrics -- 4.4 Ablation Study -- 4.5 Performance on Tail Labels -- 5 Conclusions -- References -- MGEDR: A Molecular Graph Encoder for Drug Recommendation -- 1 Introduction -- 2 Related Works -- 2.1 Drug Recommendation -- 2.2 Molecular Graph Representation -- 3 Problem Formulation -- 4 The MGEDR Model -- 4.1 Patient Encoder -- 4.2 Medicine Encoder -- 4.3 Functional Groups Encoder -- 4.4 Medicine Representation -- 4.5 Optimization -- 5 Experiments -- 5.1 Dataset and Metrics -- 5.2 Results -- 5.3 Ablations -- 6 Conclusion -- References -- Student Workshop (Poster) -- Semi-supervised Protein-Protein Interactions Extraction Method Based on Label Propagation and Sentence Embedding -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Problem Formulation -- 3.2 Overall Workflow. ; 3.3 Label Propagation -- 3.4 Sentence Embedding -- 3.5 CNN Classifier -- 4 Results -- 4.1 Datasets and Preprocessing -- 4.2 Experimental Results -- 4.3 Hyperparameter Analysis -- 5 Conclusion -- References -- Construction and Application of a Large-Scale Chinese Abstractness Lexicon Based on Word Similarity -- 1 Introduction -- 2 Data and Method -- 2.1 Data -- 2.2 Method -- 3 Experiment -- 4 Construction and Evaluation -- 5 Application -- 5.1 Cross-Language Comparison -- 5.2 Chinese Text Readability Auto-evaluation -- 6 Conclusion -- References -- Stepwise Masking: A Masking Strategy Based on Stepwise Regression for Pre-training -- 1 Introduction -- 2 Methodology -- 2.1 Three-Stage Framework -- 2.2 Stepwise Masking -- 3 Experiments -- 3.1 Datasets -- 3.2 Experimental Settings -- 3.3 Main Results -- 3.4 Effectiveness of Stepwise Masking -- 3.5 Effect of Dynamic in Stepwise Masking -- 3.6 Case Study -- 4 Conclusion and Future Work -- References -- Evaluation Workshop (Poster) -- Context Enhanced and Data Augmented W2NER System for Named Entity Recognition -- 1 Introduction -- 2 Related Work -- 3 The Proposed Approach -- 3.1 Task Definition -- 3.2 Model Structure -- 3.3 Data Augmentation -- 3.4 Result Ensemble -- 4 Experiments -- 4.1 Dataset and Metric -- 4.2 Experiment Settings -- 4.3 Baselines -- 4.4 Results and Analysis -- 5 Conclusion -- References -- Multi-task Hierarchical Cross-Attention Network for Multi-label Text Classification -- 1 Introduction -- 2 Related Work -- 2.1 Hierarchical Multi-label Text Classification -- 2.2 Representation of Scientific Literature -- 3 Methodology -- 3.1 Representation Layer -- 3.2 Hierarchical Cross-Attention Recursive Layer -- 3.3 Hierarchical Prediction Layer -- 3.4 Rebalanced Loss Function -- 4 Experiment -- 4.1 Dataset and Evaluation -- 4.2 Experimental Settings -- 4.3 Results and Discussions. ; 4.4 Module Analysis -- 5 Conclusion -- References -- An Interactive Fusion Model for Hierarchical Multi-label Text Classification -- 1 Introduction -- 2 Related Work -- 3 Task Definition -- 4 Method -- 4.1 Shared Encoder Module -- 4.2 Task-Specific Module -- 4.3 Training and Inference -- 5 Experiment -- 6 Conclusion -- References -- Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation -- 1 Introduction -- 2 Task Introduction -- 2.1 Problem Definition -- 2.2 Evaluation Metric -- 2.3 Dateset -- 3 Main Methods -- 3.1 Multi-tasking Multi-modal Dialogue Understanding -- 3.2 Scene-Aware Prompt Multi-modal Dialogue Generation -- 3.3 Training and Inference -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Main Results -- 4.3 Ablation Study -- 4.4 Online Results -- 5 Conclusion -- References -- BIT-WOW at NLPCC-2022 Task5 Track1: Hierarchical Multi-label Classification via Label-Aware Graph Convolutional Network -- 1 Introduction -- 2 Approach -- 2.1 Context-Aware Label Embedding -- 2.2 Graph-Based Hierarchical Label Modeling -- 2.3 Curriculum Learning Strategy -- 2.4 Ensemble Learning and Post Editing -- 3 Experiments -- 3.1 Dataset and Experiment Settings -- 3.2 Main Results -- 3.3 Analysis -- 4 Related Work -- 5 Conclusion -- References -- CDAIL-BIAS MEASURER: A Model Ensemble Approach for Dialogue Social Bias Measurement -- 1 Introduction -- 2 Related Work -- 2.1 Shared Tasks -- 2.2 Solution Models -- 3 Dataset -- 4 Method -- 4.1 Models Selection -- 4.2 Fine-Tuning Strategies -- 4.3 Ensembling Strategy -- 5 Result -- 5.1 Preliminary Screening -- 5.2 Model Ensemble -- 5.3 Ensemble Size Effect -- 5.4 Discussion -- 6 Conclusion -- References -- A Pre-trained Language Model for Medical Question Answering Based on Domain Adaption -- 1 Introduction -- 2 Related Work -- 2.1 Encoder-Based -- 2.2 Decoder-Based -- 2.3 Encoder-Decoder-Based. ; 3 Description of the Competition -- 3.1 Evaluation Metrics -- 3.2 Datasets -- 4 Solution -- 4.1 Model Introduction -- 4.2 Strategy -- 4.3 Model Optimization -- 4.4 Model Evaluation -- 5 Conclusion -- References -- Enhancing Entity Linking with Contextualized Entity Embeddings -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Dual Encoder -- 3.2 LUKE-Based Cross-Encoder -- 4 Experiments -- 4.1 Data -- 4.2 Candidate Retrieval -- 4.3 Candidate Reranking -- 5 Conclusion -- References -- A Fine-Grained Social Bias Measurement Framework for Open-Domain Dialogue Systems -- 1 Introduction -- 2 Related Work -- 2.1 Fine Grained Dialogue Social Bias Measurement -- 2.2 Application of Contrastive Learning in NLP Tasks -- 2.3 Application of Prompt Learning in NLP Tasks -- 3 Fine-Grain Dialogue Social Bias Measurement Framework -- 3.1 General Representation Module -- 3.2 Two-Stage Prompt Learning Module -- 3.3 Contrastive Learning Module -- 4 Experiment -- 4.1 Dataset -- 4.2 Experimental Setup -- 4.3 Results and Analysis -- 5 Conclusion -- References -- Dialogue Topic Extraction as Sentence Sequence Labeling -- 1 Introduction -- 2 Related Work -- 2.1 Dialogue Topic Information -- 2.2 Sequence Labeling -- 3 Methodology -- 3.1 Task Definition -- 3.2 Topic Extraction Model -- 3.3 Ensemble Model -- 4 Experiments -- 4.1 Dataset -- 4.2 Results and Analysis -- 5 Conclusion -- References -- Knowledge Enhanced Pre-trained Language Model for Product Summarization -- 1 Introduction -- 2 Related Work -- 2.1 Encoder-Decoder Transformer -- 2.2 Decoder-Only Transformer -- 3 Description of the Competition -- 4 Dataset Introduction -- 4.1 Textual Data -- 4.2 Image Data -- 5 Model Solution -- 5.1 Model Introduction -- 5.2 Model Training -- 6 Model Evaluation -- 7 Conclusion -- References -- Augmented Topic-Specific Summarization for Domain Dialogue Text -- 1 Introduction. ; 2 Related Work.
• Titolo autorizzato: Natural Language Processing and Chinese Computing
• ISBN: 3-031-17189-6
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910595031503321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture notes in computer science.