NII Repository (National Institute of Informatics)
Not a member yet
2035 research outputs found
Sort by
JupyterNotebookとは JupyterNotebookを使ってみよう
Get PDF研修名：2024年度情報処理技術セミナー（クラウド編）
開催期間：2024年9月6日（金）
主催：国立情報学研究所conference presentatio
VLP Methods at the MedNLP-SC Social Media Adverse Drug Event Detection of NTCIR-17
Get PDFThe VLP team participated in the MedNLP-SC subtask of the NTCIR-17. This paper reports our approach to solving the problem and discusses our experimental and official results. We present approaches which combine the training datasets using different methods, either vertically or horizontally across the languages. We use different text representation methods, either using a continuous embedding vector generated by a large pretrained language model or a discrete count vector generated by a simple bag-of-word method. Our proposed approaches achieve good performance - our system is ranked in the top two or three of the best performing systems forthe task.conference pape
Classification of cancer TNM stage from Japanese radiology report using on-premise LLM at NTCIR-17 MedNLP-SC RR-TNM subtask
Get PDFIn this manuscript, we describe our submission to the RR-TNM subtask of NTCIR-17 MedNLP-SC shared task. We took an approach to create extensive question-and-answer (Q&A) pairs related to TNM classification as a method of domain-specific augmentation. Compared to the result without data augmentation, improvement in the accuracy especially for the M stage was observed.conference pape
UDInfoLab at the NTCIR-17 FairWeb-1 Task
Get PDFProviding relevant, diverse, and fair results is crucial for informationretrieval systems. It has attracted more and more attentionbecause of issues caused by traditional relevance-centric retrieval systems.These issues include the problem of echo chambers and theincreasingly polarized online communities. Therefore, we participatedin the NTCIR-17 FairWeb-1 Task to provide group fairness toresearchers, movies, and YouTube content and submitted five runs.The runs are based on a recently proposed fair ranking framework,DLF. The experimental results demonstrate that, in many cases, DLF can improve fairness while maintaining relevance but stillneeds more exploration for ordinal fairness groups and documentswith longer text. This paper reports how the runs were constructedand discusses their performance and future work.conference pape
JPXIteam at the NTCIR-17 UFO Task
Get PDFThe JPXIteam participated in the table data extraction subtask of the NTCIR-17 UFO Task. This study outlines our methodology to address this challenge and analyzes the official results. Our approach to solving this subtask involved few-shot text classification using ChatGPT. This paper discusses the implications of these results, highlighting the contributions of this study in advancing table structure recognition.conference pape
AILABUD at the NTCIR-17 MedNLP-SC Task: Monolingual vs Multilingual Fine-tuning for ADE Classification
Get PDFThe AILAB team participated in the Social Media subtask of the NTCIR-17 MedNLP-SC Task. This paper reports our approach to solving the problem and discusses the official results. The presented model performs binary classification of the tweets and, given an UMLS term, determines whether it is present as an ADE in the tweet. Due to this design, it does not need an intermediate ADE extraction step, and it can be extended to new UMLS terms currently not present in the text. The base model used in the experiments is multilingual SapBERT, which was fine-tuned in a monolingual and multilingual setting. The best results were achieved by training the model on multilingual data.conference pape