Generating the first postoperative outpatient note requires selecting which information from heterogeneous clinical records should be reflected in the final note, rather than merely summarizing all inputs. We evaluate this task on an original 170-case set of de-identified clinical cases collected at Seoul National University Hospital (SNUH), involving two surgical divisions and five physicians. We then extend the evaluation to 1,329 cases across 10 surgery groups within the same institution to examine whether the main trends persist at a larger scale. We introduce physician- and surgery-specific same-surgery references: structured reflection maps that capture how information is selected and rewritten in prior same-surgery cases. Experiments show that these references become most effective when carried into the merge stage, suggesting that the main bottleneck is deciding what to reflect across records. We further show that cross-patient references can induce unsupported transfer from prior cases. To analyze this trade-off, we use a human-validated two-source FactScore that checks each generated fact against both the source records and the physician-written note. A lightweight grounding constraint reduces hallucination while maintaining or improving alignment with physician-written notes across divisions and LLMs.

Automatic evaluation of text simplification is important; but assessing its transformation into simpler sentences can be challenging for various reasons. However, the most commonly used metric in text simplification, SARI, fails to capture the difficulty of generating words that are not present in the references, regardless of their meaning. We propose a new learnable evaluation metric that decomposes and reconstructs sentences to simultaneously measure the similarity and difficulty of sentences within a single system. Through experiments, we confirm that it exhibited the highest similarity in correlation with the human evaluation.

Medical image captioning can reduce the workload of physicians and save time and expense by automatically generating reports. However, current datasets are small and limited, creating additional challenges for researchers. In this study, we propose a feature difference and tag information combined long short-term memory (LSTM) model for chest x-ray report generation. A feature vector extracted from the image conveys visual information, but its ability to describe the image is limited. Other image captioning studies exhibited improved performance by exploiting feature differences, so the proposed model also utilizes them. First, we propose a difference and tag (DiTag) model containing the difference between the patient and normal images. Then, we propose a multi-difference and tag (mDiTag) model that also contains information about low-level differences, such as contrast, texture, and localized area. Evaluation of the proposed models demonstrates that the mDiTag model provides more information to generate captions and outperforms all other models.

This paper presents a method of designing specific high-order dependency factor on the linear chain conditional random fields (CRFs) for named entity recognition (NER). Named entities tend to be separated from each other by multiple outside tokens in a text, and thus the first-order CRF, as well as the second-order CRF, may innately lose transition information between distant named entities. The proposed design uses outside label in NER as a transmission medium of precedent entity information on the CRF. Then, empirical results apparently demonstrate that it is possible to exploit long-distance label dependency in the original first-order linear chain CRF structure upon NER while reducing computational loss rather than in the second-order CRF.