Description
Book SynopsisNLP Applications
.-Self-Supervised Contrastive Learning for Content-Centric Speech Representation.
.-A Chunk-based Chain of Thought Prompting Method for Mitigating Over-Correction in Chinese Grammatical Error Correction.
.- Linguistic Differences between AI and Human Comments in Weibo: Detect AI-Generated Text through Stylometric Features.
.- Fine-tuning GEC Model Based on Language Family Corpus.
.- Statistically Optimized SGNS Model: Enhancing Word Vector Representation with Global Semantic Weight.
.- HFSD-V2C: Zero-Shot Visual Voice Cloning Via Hierarchical Face-Styled Diffusion Model.
.- CRAF:Cross-Modal Representation Alignment and Fusion for Speech Translation.
.- Lao-English Code-Switched Speech Synthesis Via Neural Codec Language Modeling.
.- UMAD: Enhancing LLM Debiasing via Multi-Agent Debate and Token-Level Bias Interpretation.
.- Instruction-Driven In-Context Learning for Domain-Specific Chinese Spelling Correction.
.- DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation.
Large Language Models
.- RankLLM: A multi-criteria decision-making method for LLM performance evaluation in sentiment analysis.
.- MQM-MSC: Enhancing Translation Quality Estimation Interpretability with Mask-Driven Self-Correction in Large Language Models.
.- Improving Abstract Reasoning Ability of Large Language Models through Mixture Program-based Data Synthesis.
.- RJAG: Retrieval Judgment Augmented Generation.
.- Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models.
Language Resource and Evaluation
.- Unveiling the Linguistic Acceptability Judgments of Large Language Models in Multilingual Contexts.
.- MASP: A Multilingual Dataset for Probing Scalar Modifier Understanding in LLMs.
Text Generation, Dialogue and Summarization
.- Self-Preference: An Automated Method for Preference-Aligned Data Constructed from Business Metrics.
.- TAG: Dialogue Summarization Based on Topic Segmentation and Graph Structures.
.- Enabling Real-Time Conversations with Minimal Training Costs.
Information Retrieval, Text Classification and QA
.- EDGE: Enhanced Debiased Gradient Extraction for Robust Fine-tuning.
.- BiSaGA: A Novel Bidirectional Sparse Graph Attention Adapter for Evidence-Based Fact-Checking.
ACL ARR Fast Track
.- Cross-modal Ambiguity Learning with Heterogeneous Interaction Analysis For Rumor Detection.
.- Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models.
.- DSMR-SQL: Enhancing Text-to-SQL with Dual-Strategy SQL Generation and Multi-Role SQL Selection.
Machine Translation and Multilingual Information Processing
.- Quality-aware Neural Machine Translation with Self-evaluation.
