2 citations · 4 across the 5 of their papers we have counts for
7 papers
Analyzing the Effect of Multi-task Learning for Biomedical Named Entity Recognition
Arda Akdemir, 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 requi…
Hierarchical Multi Task Learning with Subword Contextual Embeddings for Languages with Rich Morphology
Arda Akdemir, Tetsuo Shibuya, 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 externa…
Alexander polynomials of simple-ribbon knots
Kengo Kishimoto, Tetsuo Shibuya, Tatsuya Tsukamoto +1
In a previous paper, we introduced special types of fusions, so called simple-ribbon fusions on links. A knot obtained from the trivial knot by a finite sequence of simple-ribbon f…
Succinct Oblivious RAM
Taku Onodera, Tetsuo Shibuya
Reducing the database space overhead is critical in big-data processing. In this paper, we revisit oblivious RAM (ORAM) using big-data standard for the database space overhead. ORA…
Detecting Superbubbles in Assembly Graphs
Taku Onodera, Kunihiko Sadakane, Tetsuo Shibuya
We introduce a new concept of a subgraph class called a superbubble for analyzing assembly graphs, and propose an efficient algorithm for detecting it. Most assembly algorithms uti…
Homotopy, Delta-equivalence and concordance for knots in the complement of a trivial link
Thomas Fleming, Tetsuo Shibuya, Tatsuya Tsukamoto +1
Link-homotopy and self Delta-equivalence are equivalence relations on links. It was shown by J. Milnor (resp. the last author) that Milnor invariants determine whether or not a lin…