The incompleteness of knowledge base (KB) is a vital factor limiting the performance of question answering (QA). This paper proposes a novel QA method by leveraging text information to enhance the incomplete KB. The model enriches the entity representation through semantic information contained in the text, and employs graph convolutional networks to update the entity status. Furthermore, to exploit the latent structural information of text, we treat the text as hyperedges connecting entities among it to complement the deficient relations in KB, and hypergraph convolutional networks are further applied to reason on the hypergraph-formed text. Extensive experiments on the WebQuestionsSP benchmark with different KB settings prove the effectiveness of our model.
Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances. Meta-learning has been widely adopted for such a task, which trains on randomly generated few-shot tasks to learn generic data representations. Despite impressive results achieved, existing models still perform suboptimally when handling hard FSRE tasks, where the relations are fine-grained and similar to each other. We argue this is largely because existing models do not distinguish hard tasks from easy ones in the learning process. In this paper, we introduce a novel approach based on contrastive learning that learns better representations by exploiting relation label information. We further design a method that allows the model to adaptively learn how to focus on hard tasks. Experiments on two standard datasets demonstrate the effectiveness of our method.
Objective:
To summarize the characteristics of muscle-specific receptor tyrosine kinase antibody-positive myasthenia gravis (MuSK-MG) in Northeast China.
Methods:
We retrospectively collected 183 confirmed MG patients and divided them into three groups based on the type of serum antibodies: MuSK-MG (14 cases), acetylcholine receptor (AChR)-MG (130 cases), and double-seronegative (DSN)-MG (39 cases). The clinical, diagnostic, therapeutic, and prognosis data were analyzed.
Results:
MuSK antibody was detected in 26.7% of seronegative MG. The mean age of onset in MuSK-MG was 53.2 ± 13.6 years. Fifty percent of MuSK-MG patients with an onset symptom of pure ocular muscle weakness. The time from onset to other muscle groups' involvement and the time from onset to myasthenic crisis had no significant difference among the three groups (
P
> 0.05). The proportion of Osserman classification I in MuSK-MG group was lower than that in DSN-MG group. The proportion of Osserman classification IV in MuSK-MG group was higher than that in the other two groups. The incidences of other coexisting autoimmune diseases in MuSK-MG group were higher. Prognosis after the treatment of steroid combined with tacrolimus for MuSK-MG was similar to AChR-MG treated with steroid combined with an immunosuppressant agent (
P
> 0.05).
Conclusion:
Patients with MuSK-MG in Northeast China have a modestly later onset age and a proportion of patients may have a mild form of the disease with delayed disease progression. We confirmed the existence of a rare ocular MuSK-MG phenotype, a high proportion of coexisting with other autoimmune diseases, and a good response to steroids combined with tacrolimus for our MuSK-MG series.
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.