End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system is costly and time consuming. One question arises from this: how to train an end-to-end SLU with limited amounts of data? Many researchers have explored approaches that make use of other related data resources, typically by pre-training parts of the model on high-resource speech recognition. In this paper, we suggest improving the generalization performance of SLU models with a non-standard learning algorithm, Reptile. Though Reptile was originally proposed for model-agnostic meta learning, we argue that it can also be used to directly learn a target task and result in better generalization than conventional gradient descent. In this work, we employ Reptile to the task of end-to-end spoken intent classification. Experiments on four datasets of different languages and domains show improvement of intent prediction accuracy, both when Reptile is used alone and used in addition to pre-training.
The hospital discharge summaryis an essential document, containing clinical and administrative information necessary for the continuity of care after the patients are discharged from hospital. The utilization of electronic discharge summaries has grown in popularity. However, many transcription errors and spelling mistakes exit, potentially reducing the medical quality of patient care. To solve this problem, this paper presents a novel approach to detect these errors automatically by using Named entity recognition (NER). The NER model was trained by 450 discharge summaries and rich features set was used to improve the recall and precision. Experiment on the independent test set validated the good performance of NER. The follow-up error detection using the trained NER discovered that the mistakes and ambiguous information that frequently occurred in discharge summaries.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.