Natural Language Processing and Chinese Computing

TRAMA

This three-volume set constitutes the refereed proceedings of the 12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023, held in Foshan, China, during October 12–15, 2023. The 143 regular papers included in these proceedings were carefully reviewed and selected from 478 submissions. They were organized in topical sections as follows: dialogue systems; fundamentals of NLP; information extraction and knowledge graph; machine learning for NLP; machine translation and multilinguality; multimodality and explainability; NLP applications and text mining; question answering; large language models; summarization and generation; student workshop; and evaluation workshop.

SOMMARIO

Dialogue Systems.- A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training.- Retrieval-Augmented Knowledge-Intensive Dialogue.- Episode-based Prompt Learning for Any-shot Intent Detection.- CrossDial: An Entertaining Dialogue Dataset of Chinese Crosstalk.- Fundamentals of NLP.- Recurrent Transformers for Long Document Understanding.- SCA-CLS: A New Semantic-Context-Aware Framework for Community-Oriented Lexical Simplification.- A Cross-lingual Sentiment Embedding Model with Semantic and Sentiment Joint Learning.- Learning to Attentively Represent Distinctive Information for Semantic Text Matching.- Information Extraction and Knowledge Graph.- Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings.- MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion.- A Joint Entity and Relation Extraction Approach Using Dilated Convolution and Context Fusion.- Interest Aware Dual-channel Graph Contrastive Learning for Session-based Recommendation.- Chinese Event Causality Identification Based on Retrieval Enhancement.- UZNER: A Benchmark for Named Entity Recognition in Uzbek.- Evaluation Framework for Poisoning Attacks on Knowledge Graph Embeddings.- Label-guided Compressed Prototypical Network for Incremental Few-shot Text Classification.- Auxiliary Information Enhanced Span-based Model for Nested Named Entity Recognition.- DialogRE$^{C+}$: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs.- A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition.- Positive-guided Knowledge Distillation for Document-level Relation Extraction with Noisy Labeled Data.- PromptCL: Improving Event Representation via Prompt Template and Contrastive Learning.- RMGCN: Masked Graph Convolutional Networks for Relation-Aware Entity Alignment with Dangling Cases.- SymCoNLL: A Symmetry-based Approach for Document Coreference Resolution.- What Makes a Charge? Identifying Charge-Discriminative Facts with Legal Elements.- Machine Learning for NLP.-  A New Encoder Using Character and Word Feature Fusion for Chinese Math Word Problem Solving.- MarkBERT: Marking Word Boundaries Improves Chinese BERT.- MCVIE: An Effective Batch-Mode Active Learning for Multi-Label Text Classification.- Task-consistent Meta Learning for Low-resource Speech Recognition.- An Adaptive Learning Method for Solving the Extreme Learning Rate Problem of Transformer.- Machine Translation and Multilinguality.- Towards Making the Most of LLM for Translation Quality Estimation.- Towards Better Translations from Classical to Modern Chinese: A New Dataset and a New Method.- Imitation Attacks Can Steal More than You Think from Machine Translation Systems.- Monolingual Denoising with Large Language Models for Low-Resource Machine Translation.- Multimodality and Explainability.- CAMG: Context-Aware Moment Graph Network for Multimodal Temporal Activity Localization via Language.- Semantic Extension for Cross-Modal Retrieval of Medical Image-Diagnosis Report.- ECOD: A Multi-Modal Dataset for Intelligent Adjudication of E-Commerce Order Disputes.- Bounding and Filling: A Fast and Flexible Framework for Image Captioning.- NLP Applications and Text Mining.- ASKSpell: Adaptive Surface Knowledge Enhances Tokens’ Semantic Representations for Chinese Spelling Check.- Biomedical Entity Normalization Using Encoder Regularization and Dynamic Ranking Mechanism.- Legal Judgment Prediction Incorporating Guiding Cases Matching.- Punctuation Matters! Stealthy Backdoor Attack for Language Models.- SeSQL: A High-quality Large-scale Session-level Chinese Text-to-SQL Dataset.- RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling Check.- Exploiting Multiple Features for Hash Codes Learning with Semantic-Alignment-Promoting Variational Auto-encoder.- Enhancing Detailed Feedback to Chinese Writing Learners Using a Soft-Label Driven Approach and Tag-Aware Ranking Model.- Question Answering.- NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering.- Mixture-of-Experts for Biomedical Question Answering.- Fine-grained Question-Answer Matching via Sentence-aware Contrastive Self-supervised Transfer.- KARN:Knowledge Augmented Reasoning Network for Question Answering.- Large Language Models.- Creative Destruction: Can Language Models Interpret Oxymorons?.- Global Prompt Cell: A Portable Control Module for Effective Prompt Tuning.- What Events Do Pre-trained Language Models Learn from Text? Probing Event-based Commonsense Knowledge by ConfidenceSorting.- Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task.- Large Language Models are Diverse Role-Players for Summarization Evaluation.- COSYWA: Enhancing Semantic Integrity in Watermarking Natural Language Generation.- Summarization and Generation.- Multi-Step Review Generation Based on Masked Language Model for Cross-Domain Aspect-Based Sentiment Analysis.- rT5: A Retrieval-Augmented Pre-Trained Model for Ancient Chinese Entity Description Generation.- Probing Bilingual Guidance for Cross-Lingual Summarization.- Accurate, Diverse and Multiple Distractor Generation with Mixture of Experts.- Improve the Diversity and Novelty for Open-ended Neural Text Generation via Inverse Probability Weighting.- Dialogue Systems.- A Unified Generation Approach for Robust Dialogue State Tracking.- An Explicit-Memory Few-shot Joint Learning Model.- A Noise-Removal of Knowledge Graph Framework for Profile-based Spoken Language Understanding.- Bilevel Scheduled Sampling for Dialogue Generation.- Dial-QP: A Multi-Tasking and Keyword-Guided Approach for Enhancing Conversational Query Production.- Discourse Relation-Aware Multi-turn Dialogue Response Generation.

ALTRE INFORMAZIONI

• Condizione: Nuovo
• ISBN: 9783031446924
• Collana: Lecture Notes in Computer Science
• Dimensioni: 235 x 155 mm
• Formato: Brossura
• Illustration Notes: XLIII, 875 p. 245 illus., 221 illus. in color.
• Pagine Arabe: 875
• Pagine Romane: xliii