1 code implementation • 23 Jan 2022 • Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Hiroki Kanezashi, Toyotaro Suzumura, Isaiah Onando Mulang'
We further provide a theoretical analysis and prove that the spatial attention mechanism in the transformer cannot effectively capture the desired frequency response, thus, inherently limiting its expressiveness in spectral space.
no code implementations • 6 Jan 2022 • Girmaw Abebe Tadesse, William Ogallo, Catherine Wanjiru, Charles Wachira, Isaiah Onando Mulang', Vibha Anand, Aisha Walcott-Bryant, Skyler Speakman
However, there is a common lack of a principled and scalable feature selection method for efficient discovery.
no code implementations • 23 Nov 2021 • Isaiah Onando Mulang', William Ogallo, Girmaw Abebe Tadesse, Aisha Walcott-Bryant
Analyzing the behaviour of a population in response to disease and interventions is critical to unearth variability in healthcare as well as understand sub-populations that require specialized attention, but also to assist in designing future interventions.
no code implementations • 5 Nov 2021 • Catherine Wanjiru, William Ogallo, Girmaw Abebe Tadesse, Charles Wachira, Isaiah Onando Mulang', Aisha Walcott-Bryant
The pipeline included three types of feature selection techniques; Filters, Wrappers and Embedded methods to select the top K features.
no code implementations • 18 Oct 2021 • Jennifer D'Souza, Isaiah Onando Mulang', Soeren Auer
In multiple-choice exams, students select one answer from among typically four choices and can explain why they made that particular choice.
no code implementations • 29 Sep 2021 • Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Hiroki Kanezashi, Toyotaro Suzumura, Isaiah Onando Mulang'
Transformers have recently been applied in the more generic domain of graphs.
1 code implementation • Findings (ACL) 2021 • Abhishek Nadgeri, Anson Bastos, Kuldeep Singh, Isaiah Onando Mulang', Johannes Hoffart, Saeedeh Shekarpour, Vijay Saraswat
We present a novel method for relation extraction (RE) from a single sentence, mapping the sentence and two given entities to a canonical fact in a knowledge graph (KG).
1 code implementation • EACL 2021 • Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang', Saeedeh Shekarpour, Johannes Hoffart, Jens Lehmann
Our empirical study was conducted on two well-known knowledge bases (i. e., Wikidata and Wikipedia).
Ranked #1 on Entity Linking on MSNBC
1 code implementation • 18 Sep 2020 • Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Isaiah Onando Mulang', Saeedeh Shekarpour, Johannes Hoffart, Manohar Kaul
In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG).
1 code implementation • 12 Aug 2020 • Isaiah Onando Mulang', Kuldeep Singh, Chaitali Prabhu, Abhishek Nadgeri, Johannes Hoffart, Jens Lehmann
We further hypothesize that our proposed KG context can be standardized for Wikipedia, and we evaluate the impact of KG context on state-of-the-art NED model for the Wikipedia knowledge base.
Ranked #2 on Entity Disambiguation on AIDA-CoNLL