This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs' capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.
This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed. The situations in which this combination is most appropriate are characterized, including quantitative evaluation and qualitative error analysis on a variety of commonsense question answering benchmark datasets.
Recent research shows synthetic data as a source of supervision helps pretrained language models (PLM) transfer learning to new target tasks/domains. However, this idea is less explored for spatial language. We provide two new data resources on multiple spatial language processing tasks. The first dataset is synthesized for transfer learning on spatial question answering (SQA) and spatial role labeling (SpRL). Compared to previous SQA datasets, we include a larger variety of spatial relation types and spatial expressions. Our data generation process is easily extendable with new spatial expression lexicons. The second one is a real-world SQA dataset with humangenerated questions built on an existing corpus with SPRL annotations. This dataset can be used to evaluate spatial language processing models in realistic situations. We show pretraining with automatically generated data significantly improves the SOTA results on several SQA and SPRL benchmarks, particularly when the training data in the target domain is small.
We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task which is a reading comprehension on a recipe containing images and instructions. We exploit the power of attention networks, cross-modal representations, and a latent alignment space between instructions and candidate answers to solve the problem. We introduce constrained max-pooling which refines the max-pooling operation on the alignment matrix to impose disjoint constraints among the outputs of the model. Our evaluation result indicates a 19% improvement over the baselines.
BACKGROUND: Patients’ satisfaction is a fundamental factor in the quality of nursing care. The emergence of the novel Coronavirus Disease 2019 (COVID-19) and the highly contagious virus can affect nursing care by increasing the number of care-seekers. This study aimed to determine the patients’ satisfaction and related factors in patients with COVID-19 hospitalized in Taleghani Hospital, Urmia-Iran, in 2020. MATERIALS AND METHODS: This descriptive, correlational study was conducted on 196 patients with COVID-19 hospitalized in Taleghani Hospital, Urmia. Purposive convenient sampling was used to recruit participants. Study participants completed Patient Satisfaction Instrument and demographics questionnaires. Data were analyzed with the SPSS software version 25.0. RESULTS: The majority of patients (68.9%) were moderately satisfied with nursing care. Based on Pearson Correlation Analysis, only residential status had a significant inverse relationship with satisfaction level in patients with COVID-19 (r = −0.0238, P = 0.001). CONCLUSIONS: The patients’ satisfaction with nursing care was mostly at a moderate level. Thus, there is a need to educate health personnel and nurses in particular and motivate them to have active participation in achieving patients’ satisfaction with COVID-19. Notably, only the institutes that take patients’ satisfaction as a top priority can succeed in a competitive market of health services.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.