Natural Language Processing and Chinese Computing: 12th National CCF Conference, NLPCC 2023, Foshan, China, October 12–15, 2023, Proceedings, Part II(Lecture Notes in Artificial Intelligence)

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 ____ 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.

Table of Contents:
A Benchmark for Understanding Dialogue Safety in Mental Healt Support.- Fundamentals of NLP.- Span-based Pair-wise Aspect and Opinion Term Joint Extraction with Contrastive Learning.- Annotation Quality Measurement in Multi-Label Annotations.- Prompt-free Few-shot Learning with ELECTRA for Acceptability Judgment.- Dual Hierarchical Contrastive Learning for Multi-level Implicit Discourse Relation Recognition.- Towards Malay Abbreviation Disambiguation: Corpus and Unsupervised Model.- Information Extraction and Knowledge Graph.- Topic Tracking from Classification Perspective: New Chinese Dataset and Novel Temporal Correlation Enhanced Model.- A Multi-granularity Similarity Enhanced Model for Implicit Event Argument Extraction.- Multi-Perspective Feature Fusion for Event-Event Relation Extraction.- Joint Cross-Domain and Cross-Lingual Adaptation for Chinese Opinion Element Extraction.- A Relational Classification Network Integrating Multi-Scale Semantic Features.- A Novel Semantic-Enhanced Time-Aware Model for Temporal Knowledge Graph Completion.- Dual-Prompting Interaction with Entity Representation Enhancement for Event Argument Extraction.- Collective Entity Linking With Joint Subgraphs.- Coarse-to-Fine Entity Representations for Document-level Relation Extraction.- Research on Named Entity Recognition Based on Bidirectional Pointer Network and Label Knowledge Enhancement.- UKT: A Unified Knowledgeable Tuning Framework for Chinese Information Extraction.- SSUIE 1.0: A Dataset for Chinese Space Science and Utilization Information Extraction.- Extract then Adjust: A Two-Stage Approach for Automatic Term Extraction.- UniER: A Unified and Efficient Entity-Relation Extraction Method with Single-Table Modeling.- Multi-Task Biomedical Overlapping and Nested Information Extraction Model Based on Unified Framework.- NTAM: A New Transition-based Attention Model for Nested Named Entity Recognition.- Learning Well-separated and Representative Prototypes for Few-shot Event Detection.- Machine Learning for NLP.- A Frustratingly Easy Improvement for Position Embeddings via Random Padding.- IDOS: A Unified Debiasing Method via Word Shuffling.- FedEAE: Federated Learning Based Privacy-preserving Event Argument Extraction.- Event Contrastive Representation Learning Enhanced with Image Situational Information.- Promoting Open-domain Dialogue Generation through Learning Pattern Information between Contexts and Responses.- Neural News Recommendation with Interactive News Encoding and Mixed User Encoding.- Machine Translation and Multilinguality.- CD-BLI: Confidence-Based Dual Refinement for Unsupervised Bilingual Lexicon Induction.- A Novel POS-guided Data Augmentation Method for Sign Language Gloss Translation.- Faster and More Robust Low-Resource Nearest Neighbor Machine Translation.- Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation.- Multimodality and Explainability.- Two-stage Adaptation for Cross-corpus Multimodal Emotion Recognition.- Knowledgeable Salient Span Mask for Enhancing Language Models as Knowledge Base.- A Text-Image Pair Is not Enough:Language-Vision Relation Inference with Auxiliary Modality Translation.- Enriching Semantic Features for Medical Report Generation.- Entity-related Unsupervised Pretraining with Visual Prompts for Multimodal Aspect-based Sentiment Analysis.- ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles.- DialogueSMM: Emotion Recognition in Conversation with Speaker-aware Multimodal Multi-head Attention.- QAE: A Hard-label Textual Attack Considering the Comprehensive Quality of Adversarial Examples.- IMTM: Invisible Multi-Trigger Multimodal Backdoor Attack.- NLP Applications and Text Mining.- Enhancing Similar Case Matching with Event-Context Detection in Legal Intelligence.- Unsupervised Clustering with Contrastive Learning for Rumor Tracking on Social Media.- EP-Transformer: Efficient Context Propagation for Long Document.- Cross and Self Attention based Graph Convolutional Network for Aspect-based Sentiment Analysis.- KESDT: Knowledge Enhanced Shallow and Deep Transformer for Detecting Adverse Drug Reactions.- CCAE: A Corpus of Chinese-based Asian Englishes.- Emotionally-Bridged Cross-Lingual Meta-Learning for Chinese Sexism Detection.- CCPC: A Hierarchical Chinese Corpus for Patronizing and Condescending Language Detection.- FGCS: A Fine-grained Scientific Information Extraction Dataset in Computer Science Domain.- Improving Event Representation for Script Event Prediction via Data Augmentation and Integration.- Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting.- DAAL: Domain Adversarial Active Learning Based on Dual Features for Rumor Detection.- CCC: Chinese Commercial Contracts Dataset for Documents Layout Understanding.- Question Answering.- OnMKD: An Online Mutual Knowledge Distillation Framework for Passage Retrieval.- Unsupervised Clustering for Negative Sampling to Optimize Open-domain Question Answering Retrieval.- Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering.- Large Language Models.- RAC-BERT: Character Radical Enhanced BERT for Ancient Chinese.- Neural Knowledge Bank for Pretrained Transformers.- Summarization and Generation.- A Hybrid Summarization Method for Legal Judgment Documents based on Lawformer.- Enhancing Semantic Consistency in Linguistic Steganography via Denosing Auto-Encoder and Semantic-Constrained Huffman Coding.- Review Generation Combined with Feature and Instance-Based Domain Adaptation for Cross-Domain Aspect-Based Sentiment Analysis.- WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural Language Instruction.- Medical Report Generation based on Segment-Enhanced Contrastive Representation Learning.- Enhancing MOBA Game Commentary Generation With Fine-Grained Prototype Retrieval.