1 code implementation • LREC 2022 • Natalia Loukachevitch, Pavel Braslavski, Vladimir Ivanov, Tatiana Batura, Suresh Manandhar, Artem Shelmanov, Elena Tutubalina
In this paper, we describe entity linking annotation over nested named entities in the recently released Russian NEREL dataset for information extraction.
1 code implementation • 12 Dec 2023 • Love Panta, Prashant Shrestha, Brabeem Sapkota, Amrita Bhattarai, Suresh Manandhar, Anand Kumar Sah
Video moment retrieval is a challenging task requiring fine-grained interactions between video and text modalities.
1 code implementation • 21 Oct 2022 • Natalia Loukachevitch, Suresh Manandhar, Elina Baral, Igor Rozhkov, Pavel Braslavski, Vladimir Ivanov, Tatiana Batura, Elena Tutubalina
NEREL-BIO provides annotation for nested named entities as an extension of the scheme employed for NEREL.
1 code implementation • RANLP 2021 • Natalia Loukachevitch, Ekaterina Artemova, Tatiana Batura, Pavel Braslavski, Ilia Denisov, Vladimir Ivanov, Suresh Manandhar, Alexander Pugachev, Elena Tutubalina
In this paper, we present NEREL, a Russian dataset for named entity recognition and relation extraction.
no code implementations • 1 Jul 2021 • Lars Malmqvist, Tommy Yuan, Suresh Manandhar
This paper applies t-SNE, a visualisation technique familiar from Deep Neural Network research to argumentation graphs by applying it to the output of graph embeddings generated using several different methods.
no code implementations • 7 Apr 2021 • Chaitanya Kaul, Nick Pears, Suresh Manandhar
The application of deep learning to 3D point clouds is challenging due to its lack of order.
no code implementations • 4 Dec 2019 • Chaitanya Kaul, Nick Pears, Hang Dai, Roderick Murray-Smith, Suresh Manandhar
We propose a new residual block for convolutional neural networks and demonstrate its state-of-the-art performance in medical image segmentation.
no code implementations • 22 Oct 2019 • Chaitanya Kaul, Nick Pears, Hang Dai, Roderick Murray-Smith, Suresh Manandhar
Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth.
no code implementations • 18 May 2019 • Chaitanya Kaul, Nick Pears, Suresh Manandhar
But their application to processing data lying on non-Euclidean domains is still a very active area of research.
1 code implementation • 8 Feb 2019 • Chaitanya Kaul, Suresh Manandhar, Nick Pears
We propose a novel technique to incorporate attention within convolutional neural networks using feature maps generated by a separate convolutional autoencoder.
no code implementations • 25 Dec 2018 • Marcelo Sardelich, Suresh Manandhar
Stock market volatility forecasting is a task relevant to assessing market risk.
no code implementations • 29 Nov 2018 • Nils Mönning, Suresh Manandhar
Complex-valued neural networks are not a new concept, however, the use of real-valued models has often been favoured over complex-valued models due to difficulties in training and performance.