Metaphors play a crucial role in human communication, yet their comprehension remains a significant challenge for natural language processing (NLP) due to the cognitive complexity involved. According to Conceptual Metaphor Theory (CMT), metaphors map a target domain onto a source domain, and understanding this mapping is essential for grasping the nature of metaphors. Existing NLP research has focused on tasks like metaphor detection and sentiment analysis. However, there has been limited attention to identifying mappings between source and target domains. Moreover, non-English multimodal metaphor resources remain largely neglected in the literature, hindering a deeper understanding of the key elements involved in metaphor interpretation. To address this gap, we developed a Chinese multimodal metaphor advertisement dataset (namely CM3D) that includes annotations of specific target and source domains. This dataset aims at fostering further research into metaphor comprehension, particularly in non-English languages. Furthermore, we propose a Chain-of-Thought (CoT) Prompting-based Metaphor Mapping Identification Model (CPMMIM), which simulates the human cognitive process for identifying these mappings. Drawing inspiration from CoT reasoning and Bi-Level Optimization (BLO), we treat the task as a hierarchical identification problem, enabling more accurate and interpretable metaphor mapping. Our experimental results demonstrate the effectiveness of CPMMIM, highlighting its potential for advancing metaphor comprehension in NLP. Our dataset and code are both publicly available to encourage further advancements in this field.

Palliative care improves quality of life for patients and their families when facing a life-threatening illness. Studies have shown that physicians tend to over-estimate prognoses, which in combination with treatment inertia results in underutilization of end-of-life care plans. In our study, we apply machine learning methods to patients’ Electronic Health Record (EHR) data to predict patients who are likely to benefit from palliative care. Our work is based on a real-world dataset of 1,462,862 hospitalization records from the State Inpatient Database (SID) of Florida from 2012 to 2015. We examine the performance of five popular machine learning algorithms on all-cause and ten individual disease subgroups. Our experimental results demonstrate that machine learning models can achieve approximately 68% and 60% predictive accuracy for the patients who "need" and "do-not-need" end-of-life care respectively. Given the successful palliative needs identification rate is less than 50% among current hospital practices, our models can be used as an auxiliary tool to assist in palliative care resource allocation.