Natural Language Processing and Information Systems: 29th International Conference on Applications of Natural Language to Information Systems, NLDB 2024, Turin, Italy, June 25–27, 2024, Proceedings, Pa

The two-volume proceedings set LNCS 14762 and 14763 constitutes the refereed proceedings of the 29th International Conference on Applications of Natural Language to Information Systems, NLDB 2024, held in Turin, Italy, in June 25–27, 2024. The 35 full papers, 26 short papers, 3 demo papers and 8 industry track papers included in these books were carefully reviewed and selected from 141 submissions. They focus on advancements and support studies related to languages previously underrepresented, such as Arabic, Romanian, Italian and Japanese languages.

Table of Contents:
Fine-Tuning BERT On Coarse-Grained Labels: Exploring Hidden States For Fine-Grained Classification.- Studies on the Use of Large Language Models for the Automation of Business Processes in Enterprise Resource Planning Systems.- Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights.- Text Role Classification in Scientific Charts Using Multimodal Transformers.- LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning.- Unveiling Depression on Social Media: Active Learning with Human-in-the-Loop Labeling for Mental Health Data Annotation and Analysis.- All-words Pronunciation Estimation of Japanese Homographs Using Automatically Tagged Data.- I’ve got the “Answer”! Interpretation of LLMs Hidden States in Question Answering.- Improving DRS-to-Text Generation through Delexicalization and Data Augmentation.- Large Language Models for Few-Shot Automatic Term Extraction.- Data Augmentation Method Utilizing Template Sentences for Variable Definition Extraction.- Semi-supervised Named Entity Recognition for Low-Resource Languages using Dual PLMs.- Improved Models for Media Bias Detection and Subcategorization.- Grounding Toxicity in Real-World Events across Languages.-Unveiling the Hate: Generating Faithful and Plausible Explanations for Implicit and Subtle Hate Speech Detection.- The Influence of Iconicity in Transfer Learning for Sign Language Recognition.- S3: A Simple Strong Sample-Effective Multimodal Dialog System.- Body-Shaming Detection and Classification in Italian Social Media.-Adaptive Greedy Layer Pruning: Iterative Layer Pruning With Subsequent Model Repurposing.- Toward Automatic Group Membership Annotation for Group Fairness Evaluation.- REA: Refine-Estimate-Answer Prompting for Zero-Shot Relation Extraction.- Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning and Data Augmentation.- Automating Gender-Inclusive Language Modification in Italian University Administrative Documents.- An SoK of Relation Extraction Techniques in Cyber Threat Intelligence.- Shact: Disentangling and Clustering Latent Syntactic Structures from Transformer Encoders.- MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification.- SERIEMA: A Framework to Enhance Clustering Stability, Compactness, and Separation by Fusing Multimodal Data.- Exploiting Graph Embeddings from Knowledge Bases for Neural Biomedical Relation Extraction.- DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection.- EpidGPT: A Combined Strategy to Discriminate Between Redundant and New Information for Epidemiological Surveillance Systems.- Towards Generating High-Quality Knowledge Graphs by Leveraging Large Language Models.- DeepCodeGraph: A Language Model for Compile-Time Resource Optimization Using Masked Graph Autoencoders.- Design and Implementation of a Natural Language Interface for Controlling the Web of Things Devices.- IndEL: Indonesian Entity Linking Benchmark Dataset for General and Specific Domains.- Semantic Multi-Concept Annotation for Tabular Data in Financial Documents.