Natural Language Processing
Natural Language Processing (NLP) focuses on enabling computers to understand, interpret, and generate human language. Current research heavily emphasizes large language models (LLMs), exploring their capabilities in various tasks like question answering, text classification, and translation, while also addressing challenges such as bias, efficiency, and the need for better evaluation metrics. The field's significance lies in its potential to revolutionize numerous applications, from improving healthcare and education to enhancing information access and facilitating more effective human-computer interaction.
Papers
Llettuce: An Open Source Natural Language Processing Tool for the Translation of Medical Terms into Uniform Clinical Encoding
James Mitchell-White, Reza Omdivar, Esmond Urwin, Karthikeyan Sivakumar, Ruizhe Li, Andy Rae, Xiaoyan Wang, Theresia Mina, John Chambers, Grazziela Figueredo, Philip R Quinlan
Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research
Yida Mu, Mali Jin, Xingyi Song, Nikolaos Aletras
On Uncertainty In Natural Language Processing
Dennis Ulmer
A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
Shailja Gupta, Rajesh Ranjan, Surya Narayan Singh
A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization
Yucheng Chu, Hang Li, Kaiqi Yang, Harry Shomer, Hui Liu, Yasemin Copur-Gencturk, Jiliang Tang
Disentangling Latent Shifts of In-Context Learning Through Self-Training
Josip Jukić, Jan Šnajder
AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
Xiaotian Lu, Jiyi Li, Koh Takeuchi, Hisashi Kashima
StringLLM: Understanding the String Processing Capability of Large Language Models
Xilong Wang, Hao Fu, Neil Zhenqiang Gong
Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification
Kush Dubey
Word Sense Disambiguation in Native Spanish: A Comprehensive Lexical Evaluation Resource
Pablo Ortega, Jordi Luque, Luis Lamiable, Rodrigo López, Richard Benjamins
Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation
Vlad-Cristian Matei, Iulian-Marius Tăiatu, Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel
Modelando procesos cognitivos de la lectura natural con GPT-2
Bruno Bianchi, Alfredo Umfurer, Juan Esteban Kamienkowski
Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language
Vincent Beliveau, Helene Kaas, Martin Prener, Claes N. Ladefoged, Desmond Elliott, Gitte M. Knudsen, Lars H. Pinborg, Melanie Ganz