scispace - formally typeset
Search or ask a question
Institution

Naver Corporation

CompanySeongnam-si, South Korea
About: Naver Corporation is a company organization based out in Seongnam-si, South Korea. It is known for research contribution in the topics: Terminal (electronics) & Computer science. The organization has 4038 authors who have published 4294 publications receiving 35045 citations. The organization is also known as: NAVER Corporation & NAVER.


Papers
More filters
Journal Article
TL;DR: This work makes a careful conjecture that the architectural constraint of the retriever, which has been originally intended for enabling approximate search, seems to also make the model more robust in large-scale search, and proposes to distill the reader into the retriver so that the retrivers absorbs the strength of the reader while keeping its own benefit.
Abstract: The state of the art in open-domain question answering (QA) relies on an efficient retriever that drastically reduces the search space for the expensive reader. A rather overlooked question in the community is the relationship between the retriever and the reader, and in particular, if the whole purpose of the retriever is just a fast approximation for the reader. Our empirical evidence indicates that the answer is no, and that the reader and the retriever are complementary to each other even in terms of accuracy only. We make a careful conjecture that the architectural constraint of the retriever, which has been originally intended for enabling approximate search, seems to also make the model more robust in large-scale search. We then propose to distill the reader into the retriever so that the retriever absorbs the strength of the reader while keeping its own benefit. Experimental results show that our method can enhance the document recall rate as well as the end-to-end QA accuracy of off-the-shelf retrievers in open-domain QA tasks.

26 citations

Journal ArticleDOI
TL;DR: The results imply that N’Dama might have acquired distinct genotypes associated with growth and regulation of regional diseases including trypanosomiasis.
Abstract: Indigenous cattle in Africa have adapted to various local environments to acquire superior phenotypes that enhance their survival under harsh conditions. While many studies investigated the adaptation of overall African cattle, genetic characteristics of each breed have been poorly studied. We performed the comparative genome-wide analysis to assess evidence for subspeciation within species at the genetic level in trypanotolerant N’Dama cattle. We analysed genetic variation patterns in N’Dama from the genomes of 101 cattle breeds including 48 samples of five indigenous African cattle breeds and 53 samples of various commercial breeds. Analysis of SNP variances between cattle breeds using wMI, XP-CLR, and XP-EHH detected genes containing N’Dama-specific genetic variants and their potential associations. Functional annotation analysis revealed that these genes are associated with ossification, neurological and immune system. Particularly, the genes involved in bone formation indicate that local adaptation of N’Dama may engage in skeletal growth as well as immune systems. Our results imply that N’Dama might have acquired distinct genotypes associated with growth and regulation of regional diseases including trypanosomiasis. Moreover, this study offers significant insights into identifying genetic signatures for natural and artificial selection of diverse African cattle breeds.

26 citations

Journal ArticleDOI
TL;DR: Observations in the case of a 34-year-old Korean man who had P. multiflorum Thunb-induced hepatitis and reactivation of pulmonary tuberculosis caused by bone marrow suppression, which developed simultaneously suggest that the material induces bothBone marrow suppression and hepatotoxicity.
Abstract: Several cases of Polygonum multiflorum Thunb-induced hepatitis have been reported worldwide. Anthraquinone is an active ingredient of P. multiflorum Thunb. that has been thought to play a role in its hepatotoxicity. Here we report the case of a 34-year-old Korean man who had P. multiflorum Thunb-induced hepatitis and reactivation of pulmonary tuberculosis caused by bone marrow suppression, which developed simultaneously. He was admitted to our hospital with recently developed fatigue and aggravated jaundice. He was a previously healthy man except for the sequelae of pulmonary tuberculosis seen on chest X-ray. He had a 30-day history of ingesting the root of P. multiflorum as a form of liquor and tea. The patient was diagnosed with P. multiflorum Thunb-induced hepatitis after excluding all other potential causes of acute hepatitis. Liver function gradually improved following the total cessation of the consumption of the material. However, he suffered from spiking fever with progressive pancytopenia during the hospital stay. A bone marrow biopsy showed markedly hypocellular marrow, suggesting transient bone marrow suppression, which was probably caused by extrinsic factors such as drugs, toxins, and viral infection. Although he began to complain of a dry cough, repeated sputum investigations revealed positive acid-fast bacillus staining. The fever subsided and pancytopenia improved after treatment for pulmonary tuberculosis. These observations suggest that P. multiflorum Thunb induces both bone marrow suppression and hepatotoxicity.

26 citations

Posted Content
TL;DR: In this article, an attention-based meta-network is proposed to learn relative similarities between features, and applies identified similarities to control distillation intensities of all possible pairs, which improves the performance on model compression and transfer learning tasks.
Abstract: Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network Most studies manually tie intermediate features of the teacher and student, and transfer knowledge through pre-defined links However, manual selection often constructs ineffective links that limit the improvement from the distillation There has been an attempt to address the problem, but it is still challenging to identify effective links under practical scenarios In this paper, we introduce an effective and efficient feature distillation method utilizing all the feature levels of the teacher without manually selecting the links Specifically, our method utilizes an attention-based meta-network that learns relative similarities between features, and applies identified similarities to control distillation intensities of all possible pairs As a result, our method determines competent links more efficiently than the previous approach and provides better performance on model compression and transfer learning tasks Further qualitative analyses and ablative studies describe how our method contributes to better distillation The implementation code is available at this http URL

26 citations

Journal ArticleDOI
TL;DR: A convolutional neural network tailored to the task of TLSA, the TCNN leverages the distance information between the target word and its neighboring words to learn the importance of each word to the target.

26 citations


Authors

Showing all 4041 results

NameH-indexPapersCitations
Andrea Vedaldi8930563305
Sunghun Kim5111512994
Eric Gaussier412318203
Un Ju Jung39985696
Hyun-Soo Kim374215650
Gabriela Csurka3714510959
Nojun Kwak342346026
Young-Jin Park312573759
Sung Joo Kim311963078
Jae-Hoon Kim303235847
Jung-Ryul Lee292223322
Joon Son Chung28734900
Ok-Hwan Lee271632896
Diane Larlus27694722
Jung Goo Lee261421917
Network Information
Related Institutions (5)
Kyungpook National University
42.1K papers, 834.6K citations

80% related

Pusan National University
45K papers, 819.3K citations

80% related

Korea University
82.4K papers, 1.8M citations

80% related

Seoul National University
138.7K papers, 3.7M citations

79% related

Chungnam National University
32.1K papers, 543.3K citations

79% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20226
2021144
2020174
2019138
201882
201764