Publication List

2018

  • Marzena Karpinska, Bofang Li, Anna Rogers, and Aleksandr Drozd. Subcharacter information in japanese embeddings: when is it worth it? In In Proceedings of the Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP (RELNLP) 2018, to appear. ACL, 2018.
    [BibTeX▼]
  • Bofang Li, Aleksandr Drozd, Tao Liu, and Xiaoyong Du. Subword-level composition functions for learning word embeddings. In Proceedings of The 2nd Workshop on Subword and Character level models in NLP (SCLeM), 38–48. ACL, 2018.
    [full text] [BibTeX▼]

2017

  • Bofang Li, Tao Liu, Zhe Zhao, Buzhou Tang, Aleksandr Drozd, Anna Rogers, and Xiaoyong Du. Investigating different syntactic context types and context representations for learning word embeddings. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2421–2431. 2017.
    [full text] [BibTeX▼]
  • Anna Rogers, Aleksandr Drozd, and Bofang Li. The (too many) problems of analogical reasoning with word vectors. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (* SEM 2017), 135–148. 2017.
    [full text] [BibTeX▼]

2016

  • Anna Gladkova, Aleksandr Drozd, and Satoshi Matsuoka. Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't. In Proceedings of the NAACL Student Research Workshop, 8–15. 2016.
    [full text] [BibTeX▼]
  • Anna Gladkova and Aleksandr Drozd. Intrinsic evaluations of word embeddings: what can we do better? In Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, 36–42. 2016.
    [full text] [BibTeX▼]
  • H. Shamoto, K. Shirahata, A. Drozd, H. Sato, and S. Matsuoka. Gpu-accelerated large-scale distributed sorting coping with device memory capacity. IEEE Transactions on Big Data, 2(1):57–69, March 2016. doi:10.1109/TBDATA.2015.2511001.
    [BibTeX▼]
  • Aleksandr Drozd, Olaf Witkowski, Satoshi Matsuoka, and Takashi Ikegami. Critical mass in the emergence of collective intelligence: a parallelized simulation of swarms in noisy environments. Artificial Life and Robotics, 21(3):317–323, Sep 2016. URL: https://doi.org/10.1007/s10015-016-0303-8, doi:10.1007/s10015-016-0303-8.
    [abstract▼] [BibTeX▼]
  • Aleksandr Drozd, Anna Gladkova, and Satoshi Matsuoka. Word embeddings, analogies, and machine learning: beyond king-man+ woman= queen. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 3519–3530. 2016.
    [full text] [BibTeX▼]
  • M. Bysiek, A. Drozd, and S. Matsuoka. Migrating legacy fortran to python while retaining fortran-level performance through transpilation and type hints. In 2016 6th Workshop on Python for High-Performance and Scientific Computing (PyHPC), volume, 9–18. Nov 2016. doi:10.1109/PyHPC.2016.006.
    [BibTeX▼]

2015

  • Aleksandr Drozd, Anna Gladkova, and Satoshi Matsuoka. Discovering aspectual classes of russian verbs in untagged large corpora. In Data Science and Data Intensive Systems (DSDIS), 2015 IEEE International Conference on, 61–68. IEEE, 2015.
    [full text] [BibTeX▼]
  • Aleksandr Drozd, Anna Gladkova, and Satoshi Matsuoka. Python, performance, and natural language processing. In Proceedings of the 5th Workshop on Python for High-Performance and Scientific Computing, 1. ACM, 2015.
    [BibTeX▼]

2014

  • Aleksandr Drozd and Satoshi Matsuoka. Hpc and interactive big data analytics: case study of distributional semantics. In Proceedings of IPSJ SIG Technical Reports HPC-146. Naha, Oct 2014.
    [BibTeX▼]
  • Hideyuki Shamoto, Koichi Shirahata, Aleksandr Drozd, Hitoshi Sato, and Satoshi Matsuoka. Large-scale distributed sorting for gpu-based heterogeneous supercomputers. In Proceedings of 2014 IEEE International Conference on Big Data (IEEE BigData 2014). 2014. (to appear).
    [BibTeX▼]
  • A. Drozd, M. Pericàs, and S. Matsuoka. Efficient string sorting on multi - and many-core architectures. In 2014 IEEE International Congress on Big Data, volume, 637–644. June 2014. doi:10.1109/BigData.Congress.2014.97.
    [BibTeX▼]

2013

  • Aleksandr Drozd, Naoya Maruyama, and Satoshi Matsuoka. A multi gpu read alignment algorithm with model-based performance optimization. In Michel Daydé, Osni Marques, and Kengo Nakajima, editors, High Performance Computing for Computational Science - VECPAR 2012, 270–277. Berlin, Heidelberg, 2013. Springer Berlin Heidelberg.
    [abstract▼] [BibTeX▼]
  • Aleksandr Drozd, Naoya Maruyama, and Satoshi Matsuoka. A multi gpu read alignment algorithm with model-based performance optimization. In High Performance Computing for Computational Science - VECPAR 2012, 7851, 270–277. Springer-Verlag, 2013. URL: http://dx.doi.org/10.1007/978-3-642-38718-0_27, doi:10.1007/978-3-642-38718-0_27.
    [BibTeX▼]
  • Drozd Aleksandr and Matsuoka Satoshi. Msd radix string sort on gpu: longer keys, shorter alphabets. 研究報告計算機アーキテクチャ(ARC), 2013(21):1–6, dec 2013. URL: https://ci.nii.ac.jp/naid/170000079468/en/, doi:.
    [BibTeX▼]

2012

  • Aleksandr Drozd, Naoya Maruyama, and Satoshi Matsuoka. Sequence alignment on massively parallel heterogeneous systems. In in proceedings of IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum, 2498 – 2501. 2012.
    [BibTeX▼]

2011

  • Aleksandr Drozd, Naoya Maruyama, and Satoshi Matsuoka. Fast read alignment with burrows wheeler transform: the gpu perspective. In Proceedings of the 24th Summer United Workshops on Parallel, Distributed, and Cooperative Processing (SWoPP 2011), 341. 2011.
    [BibTeX▼]

2009

  • Drozd A.A. Gladkova G.P. Towards easier querying of xml-based linguistic corpora. Taurida Bulletin of Mathematics and Informatics., 2:71–77, 2009.
    [BibTeX▼]