Arda Akdemir

Arda Akdemir

Auto-generated profile, based on publicly available information

Arda Akdemir

University of Tokyo

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 April 2020 in BMC Bioinformatics
Verified
Journal Article
Open access
YZYao-zhong Zhang
Yao-zhong Zhang
AAArda Akdemir
Arda Akdemir
GTGeorg Tremmel
Georg Tremmel
SISeiya Imoto
Seiya Imoto
SMSatoru Miyano
Satoru Miyano
RYRui Yamaguchi
Rui Yamaguchi
Background: Nanopore sequencing is a rapidly developing third-generation sequencing technology, which can generate long nucleotide reads of molecules within a portable device in real-time. Through detecting the change of ion currency signals during a DNA/RNA fragment’s pass through a nanopore, genotypes are determined. Currently, the accuracy of nanopore basecalling has a higher error rate than the basecalling of short-read sequencing. Through utilizing deep neural networks, the-state-of-the art nanopore basecallers achieve basecalling accuracy in a range from 85% to 95%. Result: In this work, we proposed a novel basecalling approach from a perspective of instance segmentation. Different from previous approaches of doing typical sequence labeling, we formulated the basecalling problem as a multi-label segmentation task. Meanwhile, we proposed a refined U-net model which we call UR-net that can model sequential dependencies for a one-dimensional segmentation task. The experiment results show that the proposed basecaller URnano achieves competitive results on the in-species data, compared to the recently proposed CTC-featured basecallers. Conclusion: Our results show that formulating the basecalling problem as a one-dimensional segmentation task is a promising approach, which does basecalling and segmentation jointly.

7 October 2019 in Computación y Sistemas
Verified
Journal Article
Closed access
PDF file
AAArda Akdemir
Arda Akdemir
TGTunga Güngör
Tunga Güngör
Joint Learning of Named Entity Recognition and Dependency Parsing using Separate Datasets

24 July 2019 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
AAArda Akdemir
Arda Akdemir
TGTunga Güngör
Tunga Güngör

13 November 2021
Verified
Book Chapter
Closed access
PDF file
AAArda Akdemir
Arda Akdemir
TSTetsuo Shibuya
Tetsuo Shibuya
TGTunga Güngör
Tunga Güngör

26 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
AAArda Akdemir
Arda Akdemir
TSTetsuo Shibuya
Tetsuo Shibuya
TGTunga Güngör
Tunga Güngör
Morphological information is important for many sequence labeling tasks in Natural Language Processing (NLP). Yet, existing approaches rely heavily on manual annotations or external software to capture this information. In this study, we propose using subword contextual embeddings to capture the morphological information for languages with rich morphology. In addition, we incorporate these embeddings in a hierarchical multi-task setting which is not employed before, to the best of our knowledge. Evaluated on Dependency Parsing (DEP) and Named Entity Recognition (NER) tasks, which are shown to benefit greatly from morphological information, our final model outperforms previous state-of-the-art models on both tasks for the Turkish language. Besides, we show a net improvement of 18.86% and 4.61% F-1 over the previously proposed multi-task learner in the same setting for the DEP and the NER tasks, respectively. Empirical results for five different MTL settings show that incorporating subword contextual embeddings brings significant improvements for both tasks. In addition, we observed that multi-task learning consistently improves the performance of the DEP component.

1 November 2020 in arXiv
Verified
Preprint
Open access
PDF file
AAArda Akdemir
Arda Akdemir
TSTetsuo Shibuya
Tetsuo Shibuya
Developing high-performing systems for detecting biomedical named entities has major implications. State-of-the-art deep-learning based solutions for entity recognition often require large annotated datasets, which is not available in the biomedical domain. Transfer learning and multi-task learning have been shown to improve performance for low-resource domains. However, the applications of these methods are relatively scarce in the biomedical domain, and a theoretical understanding of why these methods improve the performance is lacking. In this study, we performed an extensive analysis to understand the transferability between different biomedical entity datasets. We found useful measures to predict transferability between these datasets. Besides, we propose combining transfer learning and multi-task learning to improve the performance of biomedical named entity recognition systems, which is not applied before to the best of our knowledge.