Figure - uploaded by Ignatius M. Ezeani
Content may be subject to copyright.
Download
View publication
Word categories for odd word dataset

Word categories for odd word dataset

Source publication
Fig. 2. Worst-to-Best Word Similarity Correlation Performance
Igbo diacritic complexity
Igbo and English models: vocabulary, vector and training data sizes
Instances of the wordkey akwa in context
+1 Word categories for odd word dataset
Multi-task projected embedding for Igbo
Conference Paper
Full-text available
  • Sep 2018
NLP research on low resource African languages is often impeded by the unavailability of basic resources: tools, techniques, annotated corpora, and datasets. Besides the lack of funding for the manual development of these resources, building from scratch will amount to the reinvention of the wheel. Therefore, adapting existing techniques and models...
Cite
Download full-text

Context in source publication

Context 1
... cereal, dinner, lunch → "cereal". We created four simple categories of words Igbo words ( Table 5) that should naturally be mutually exclusive. Test instances were built by randomly selecting and shuffling three words from one category and one from another e.g. ...

Similar publications

Figure 1: (a), (b): Visual example of generating training data for
Theoretical Understandings of Product Embedding for E-commerce Machine Learning
Preprint
Full-text available
  • Feb 2021
Product embeddings have been heavily investigated in the past few years, serving as the cornerstone for a broad range of machine learning applications in e-commerce. Despite the empirical success of product embeddings, little is known on how and why they work from the theoretical standpoint. Analogous results from the natural language processing (N...
View