Improving Natural Language Inference Using External Knowledge in the Science Questions Domain

Wang, Xiaoyan; Kapanipathi, Pavan; Musa, Ryan; Yu, Mo; Talamadupula, Kartik; Abdelaziz, Ibrahim; Chang, Maria Hsia; Fokoue, Achille; Makni, Bassem; Mattei, Nicholas; Witbrock, Michael

doi:10.48550/arxiv.1809.05724

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge graph: Structured domain knowledge, often in graph-form, has been utilized to achieve more robust inferences over purely data-driven models. For example, [19] present a framework to enable the use of various kinds of external knowledge bases to retrieve relevant answers to a given question. It provides a graph-based model which maps text phrases to concepts in the knowledge graph using several strategies.…”

Section: Related Workmentioning

confidence: 99%

Phenotypical ontology driven framework for multi-task learning

Ghalwash¹,

Yao²,

Chakraporty³

et al. 2021

Proceedings of the Conference on Health, Inference, and Learning

View full text Add to dashboard Cite

Despite the large number of patients in Electronic Health Records (EHRs), the subset of usable data for modeling outcomes of specific phenotypes are often imbalanced and of modest size. This can be attributed to the uneven coverage of medical concepts in EHRs. In this paper, we propose OMTL, an Ontology-driven Multi-Task Learning framework, that is designed to overcome such data limitations. The key contribution of our work is the effective use of knowledge from a predefined well-established medical relationship graph (ontology) to construct a novel deep learning network architecture that mirrors this ontology. It can effectively leverage knowledge from a well-established medical relationship graph (ontology) by constructing a deep learning network architecture that mirrors this graph. This enables common representations to be shared across related phenotypes, and was found to improve the learning performance. The proposed OMTL naturally allows for multitask learning of different phenotypes on distinct predictive tasks. These phenotypes are tied together by their semantic distance according to the external medical ontology. Using the publicly available MIMIC-III database, we evaluate OMTL and demonstrate its efficacy on several real patient outcome predictions over state-of-the-art multi-task learning schemes.

show abstract

Section: Related Workmentioning

confidence: 99%

Phenotypical ontology driven framework for multi-task learning

Ghalwash¹,

Yao²,

Chakraporty³

et al. 2021

Proceedings of the Conference on Health, Inference, and Learning

View full text Add to dashboard Cite

show abstract

“…After getting vector representation for entities or relations, they can be used to optimize sentence alignment like (Chen et al, 2018). Some efforts have also been made to generate knowledge enhanced representations for premise-hypothesis pairs and then used to benefit the final classification like (Wang et al, 2018b).…”

Section: Human-authorized External Knowledge Integrationmentioning

confidence: 99%

Enhancing Unsupervised Pretraining with External Knowledge for Natural Language Inference

Yang

Zhu

Zhao

et al. 2019

Advances in Artificial Intelligence

View full text Add to dashboard Cite

While recent research on natural language inference has considerably benefited from large annotated datasets (Williams et al., 2017;Bowman et al., 2015), the amount of inferencerelated knowledge (including commonsense) provided in the annotated data is still rather limited. There have been two lines of approaches that can be used to further address the limitation: (1) unsupervised pretraining can leverage knowledge in much larger unstructured text data; (2) structured (often humancurated) knowledge has started to be considered in neural-network-based models for NLI. An immediate question is whether these two approaches complement each other, or how to develop models that can bring together their advantages. In this paper, we propose models that leverage structured knowledge in different components of pre-trained models. Our results show that the proposed models perform better than previous BERT-based state-of-the-art models. Although our models are proposed for NLI, they can be easily extended to other sentence or sentence-pair classification problems.

show abstract