E-grāmata: Natural Language Processing and Chinese Computing: 13th National CCF Conference, NLPCC 2024, Hangzhou, China, November 1-3, 2024, Proceedings, Part III

Improving Causal Inference of Large Language Models with SCM Tools.- A
Privacy-Preserving Framework for Medical Chatbot based on LLM with Retrieval
Augmented Generation.- Regularized Continual Learning for Large-Scale
Language Models via Probing.- LasQ: Largest Singular Components fine-tuning
for LLMs with Quantization.- MultiAICL: Multi-Task Tuning for Augmented
In-Context Learning in Text Style Transfer.- What is the best model?
Application-driven Evaluation for Large Language Models.-Sparse Mixture of
Experts Language Models Excel in Knowledge Distillation.- Evaluation and
Analysis of the Chinese Semantic Dependency Understanding Ability of Large
Language Models.- Reparameterization-based Parameter-Efficient Fine-Tuning
Methods for Large Language Models: A Systematic Survey.- SACL: Sequential
Augmentation with Curriculum Learning in Dataset Level.- Classifiers Guided
Controllable Text Generation for Discrete Diffusion Language Models.-
AugMixSpeech: A Data Augmentation Method and Consistency Regularization for
Mandarin Automatic Speech Recognition.- FIRP: Faster LLM inference via future
intermediate representation prediction.- Margin Discrepancy-based Adversarial
Training for Multi-Domain Text Classification.- Effective Knowledge Graph
Embedding with Quaternion Convolutional Networks.- Improving End-to-End
Speech Translation with Progressive Dual Encoding.- Assessing Translation
Quality of Hypotactic Structure for Chinese-to-English Machine Translation.-
Understanding and Improving Low-Resource Neural Machine Translation with
Shallow Features.- Improving Non-autoregressive Machine Translation with
Error Exposure and Consistency Regularization.- Neural Chat Translation as
Online Document-to-Document Translation.- Autogenerated MQM Data for Quality
Estimation based on Sequence Labeling.- Pruning Residual Networks in
Multilingual Neural Machine Translation to Improve Zero-shot Translation.-
Leveraging Parameter-Efficient Fine-Tuning for Multilingual Abstractive
Summarization.- Improving Automatic Post-editing with Error Prompts Extracted
from Quality Estimation.- Progressive and Consistent Subword Regularization
for Neural Machine Translation.- Language-Emphasized Cross-Lingual In-Context
Learning for Multilingual LLM.- A Multilevel Interaction Network Framework
for Multimodal Entity Linking.- Evaluating the Fidelity of Image Captioning
via Weighted Boolean Question Answering.- Optimized Conversational Gesture
Generation with Enhanced Motion Feature Extraction and Cascaded Generator.-
Exploring the Potential of Prompting Methods in Low-resource Speech
Recognition with Whisper.- RAVL: A Retrieval-Augmented Visual Language Model
Framework for Knowledge-Based Visual Question Answering.- ASRLM: ASR-Robust
Language Model Pre-Training via Generative and Discriminative learning.-
DFS-QA: Dynamic Frame Selection for Better Video Question Answering.- Deep
Foreground-Background Weighted Cross-Modal Hashing.- Graph Interpretation of
Image-Text matching: Link Prediction on Concept-Enhanced Cross-Modal Graph.-
Multi-Granularity Semantic Guided Transformer for Radiology Report
Generation.- Steganographic Text Generation Based on Large Language Models in
Dialogue Scenarios.- A Novel ICD Coding Method Based on Associated and
Hierarchical Code Description Distillation.