Natural Language Processing and Chinese Computing [electronic resource] : 10th CCF International Conference, NLPCC 2021, Qingdao, China, October 13–17, 2021, Proceedings, Part I /

Oral - Fundamentals of NLP -- Coreference Resolution: Are the eliminated spans totally worthless? -- Chinese Macro Discourse Parsing on Dependency Graph Convolutional Network -- Predicting Categorial Sememe for English-Chinese Word Pairs via Representations in Explainable Sememe Space -- Multi-Level Cohesion Information Modeling for Better Written and Dialogue Discourse Parsing -- ProPC: A Dataset for In-domain and Cross-Domain Proposition Classification Tasks -- CTRD: A Chinese Theme-Rheme Discourse Dataset -- Machine Translation and Multilinguality -- Learning to Select Relevant Knowledge for Neural Machine Translation -- Contrastive Learning for Machine Translation Quality Estimation -- Sentence-State LSTMs for Sequence-to-Sequence Learning -- Guwen-UNILM: Machine Translation Between Ancient and Modern Chinese Based on Pre-Trained Models -- Adaptive Transformer for Multilingual Neural Machine Translation -- Improving Non-Autoregressive Machine Translation with Soft-Masking -- Machine Learning for NLP -- AutoNLU: Architecture Search for Sentence and Cross-sentence Attention Modeling with Re-designed Search Space -- AutoTrans: Automating Transformer Design via Reinforced Architecture Search -- A Word-level Method for Generating Adversarial Examples Using Whole-sentence Information -- RAST: A Reward Augmented Model for Fine-Grained Sentiment Transfer -- Pre-trained Language models for Tagalog with Multi source data -- Accelerating Pretrained Language Model Inference Using Weighted Ensemble Self-Distillation -- Information Extraction and Knowledge Graph -- Employing Sentence Compression to improve Event Coreference Resolution -- BRCEA: Bootstrapping Relation-aware Cross-lingual Entity Alignment -- Employing Multi-granularity Features to Extract Entity Relation in Dialogue -- Attention Based Reinforcement Learning with Reward Shaping for Knowledge Graph Reasoning -- Entity-Aware Relation Representation Learning for Open Relation Extraction -- ReMERT: Relational Memory-based Extraction for Relational Triples -- Recognition of Nested Entity with Dependency Information -- HAIN: Hierarchical Aggregation and Inference Network for Document-Level Relation Extraction -- Incorporate Lexicon into Self-training: A Distantly Supervised Chinese Medical NER -- Summarization and Generation -- Diversified Paraphrase Generation with Commonsense Knowledge Graph -- Explore Coarse-grained Structures for Syntactically Controllable Paraphrase Generation -- Chinese Poetry Generation with Metrical Constraints -- CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level -- Question Generation from Code Snippets and Programming Error Messages -- Extractive Summarization of Chinese Judgment Documents via Sentence Embedding and Memory Network -- Question Answering -- ThinkTwice: A Two-Stage Method for Long-Text Machine Reading Comprehension -- EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension -- Dialogue Systems -- Knowledge-Grounded Dialogue with Reward-Driven Knowledge Selection -- Multi-Intent Attention and Top-k Network with Interactive Framework for Joint Multiple Intent Detection and Slot Filling -- Enhancing Long-Distance Dialogue History Modeling for Better Dialogue Ellipsis and Coreference Resolution -- Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation -- Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF -- Cross-domain Slot Filling with Distinct Slot Entity and Type Prediction -- Social Media and Sentiment Analysis -- Semantic Enhanced Dual-channel Graph Communication Network for Aspect-based Sentiment Analysis -- Highway-Based Local Graph Convolution Network For Aspect Based Sentiment Analysis -- Dual Adversarial Network Based on BERT for Cross-domain Sentiment Classification -- Syntax and Sentiment Enhanced BERT for Earliest Rumor Detection -- Aspect-Sentiment-Multiple-Opinion Triplet Extraction -- Locate and Combine: A Two-Stage Framework for Aspect-Category Sentiment Analysis -- Emotion Classification with Explicit and Implicit Syntactic Information -- MUMOR:A Multimodal Dataset for Humor Detection in Conversations -- NLP Applications and Text Mining -- Advertisement Extraction from Content Marketing Articles via Segment-aware Sentence Classification -- Leveraging Lexical Common-Sense Knowledge for Boosting Bayesian Modeling -- Aggregating inter-viewpoint relationships of user's review for accurate recommendation -- A Residual Dynamic Graph Convolutional Network for Multi-label Text Classification -- Sentence Ordering by Context-enhanced Pairwise Comparison -- A Dual-Attention Neural Network for Pun Location and Using Pun-Gloss Pairs for Interpretation -- A Simple Baseline for Cross-domain Few-shot Text Classification -- Shared Component Cross Punctuation Clauses Recognition in Chinese -- BERT-KG:A Short Text Classification Model Based on Knowledge Graph and Deep Semantics -- Uncertainty-aware Self-paced Learning for Grammatical Error Correction -- Metaphor Recognition and Analysis via Data Augmentation -- Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning -- Multimodality and Explainability -- Skeleton-Based Sign Language Recognition with Attention-enhanced Graph Convolutional Networks -- XGPT: Cross-modal Generative Pre-Training for Image Captioning -- An Object-Extensible Training Framework for Image Captioning -- Relation-aware Multi-hop Reasoning for Visual Dialog -- Multi-Modal Sarcasm Detection Based on Contrastive Attention Mechanism.

This two-volume set of LNAI 13028 and LNAI 13029 constitutes the refereed proceedings of the 10th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2021, held in Qingdao, China, in October 2021. The 66 full papers, 23 poster papers, and 27 workshop papers presented were carefully reviewed and selected from 446 submissions. They are organized in the following areas: Fundamentals of NLP; Machine Translation and Multilinguality; Machine Learning for NLP; Information Extraction and Knowledge Graph; Summarization and Generation; Question Answering; Dialogue Systems; Social Media and Sentiment Analysis; NLP Applications and Text Mining; and Multimodality and Explainability.