Chinese Computational Linguistics

Fundamental Theory and Methods of Computational Linguistics.- The Contextualized Representation of Collocation.- Information Retrieval, Dialogue and Question Answering.- Ask to Understand: Question Generation for Multi-hop Question Answering.- Learning on Structured Documents for Conditional Question Answering.- Overcoming Language Priors with Counterfactual Inference for Visual Question Answering.- Rethinking Label Smoothing on Multi-hop Question Answering.- Text Generation, Dialogue and Summarization.- Unsupervised Style Transfer in News Headlines via Discrete Style Space.- Lexical Complexity Controlled Sentence Generation for Language Learning.- Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning.- Knowledge Graph and Information Extraction.- Document Information Extraction via Global Tagging.- A Distantly-Supervised Relation Extraction Method Based on Selective Gate and Noise Correction.- Improving Cascade Decoding with Syntax-aware Aggregator and Contrastive Learning for Event Extraction.- TERL: Transformer Enhanced Reinforcement Learning for Relation Extraction.- P-MNER: Cross Modal Correction Fusion Network with Prompt Learning for Multimodal Named Entity Recognitiong.- Self Question-answering: Aspect Sentiment Triplet Extraction via a Multi-MRC Framework based on Rethink Mechanism.- Enhancing Ontology Knowledge for Domain-Specific Joint Entity and Relation Extraction.- Machine Translation and Multilingual Information Processing.- FACT:A Dynamic Framework for Adaptive Context-Aware Translation.- Language Resource and Evaluation.- MCLS: A Large-Scale Multimodal Cross-Lingual Summarization Dataset.- CHED: A Cross-Historical Dataset with a Logical Event Schema for Classical Chinese Event Detection.- Training NLI Models Through Universal Adversarial Attack.- Pre-trained Language Models.- Revisiting k-NN for Fine-tuning Pre-trained Language Models.- Adder Encoder for Pre-trained Language Model.- Exploring Accurate and Generic Simile Knowledge from Pre-trained Language Models.- Social Computing and Sentiment Analysis.- Learnable Conjunction Enhanced Model for Chinese Sentiment Analysis.- Enhancing Implicit Sentiment Learning via the Incorporation of Part-of-Speech for Aspect-based Sentiment Analysis.- Improving Affective Event Classification with Multi-Perspective Knowledge Injection.- NLP Applications.- Adversarial Network with External Knowledge for Zero-Shot Stance Detection.- Few-Shot Charge Prediction with Multi-Grained Features and Mutual Information.- SentBench: Comprehensive Evaluation of Self-Supervised Sentence Representation with Benchmark Construction.