162 citations · 1.2k across the 78 of their papers we have counts for
7 papers · 1 filter
The Challenge of Diacritics in Yoruba Embeddings
Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki
The major contributions of this work include the empirical establishment of a better performance for Yoruba embeddings from undiacritized (normalized) dataset and provision of new…
Corpora Compared: The Case of the Swedish Gigaword & Wikipedia Corpora
Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki
In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size. Natural lan…
Exploring Swedish & English fastText Embeddings for NER with the Transformer
Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki
In this paper, our main contributions are that embeddings from relatively smaller corpora can outperform ones from larger corpora and we make the new Swedish analogy test set publi…
Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks
Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki
Word2Vec is a prominent model for natural language processing (NLP) tasks. Similar inspiration is found in distributed embeddings for new state-of-the-art (SotA) deep neural networ…
Pretraining Image Encoders without Reconstruction via Feature Prediction Loss
Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki
This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced d…
HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statistics
Pedro Alonso, Kumar Shridhar, Denis Kleyko +2
Recent advances in Deep Learning have led to a significant performance increase on several NLP tasks, however, the models become more and more computationally demanding. Therefore,…