Publications

Legal-BigBird: An Adapted Long-Range Transformer for Legal Documents

Published in Black in AI Workshop NeurIPS 2021, 2021

This paper is about the fine-tuning of the linear scaling Transformer model Bigbird on legal corpora, then the resulting model as an off-the-shelf encoder for retrival task on legal court cases.

Recommended citation: Loic Kwae Dassi. Legal-BigBird: An Adapted Long-Range Transformer for Legal Documents. NeurIPS 2021 Workshop: Black in AI, 2021. https://www.researchgate.net/profile/Loic-Kwate-Dassi/publication/356930560_Legal-BigBird_An_Adapted_Long-Range_Transformer_for_Legal_Documents/links/61b5fdee63bbd9324289b54e/Legal-BigBird-An-Adapted-Long-Range-Transformer-for-Legal-Documents.pdf

Identification of Enzymatic Active Sites with Unsupervised Language Modeling

Published in ACS Spring 2022, ELLIS Workshop for Molecule Discovery, AI for Science: Mind the Gaps Neurips Workshop, 2021

This paper is about using language modeling for enzymatic active sites recognition.

Recommended citation: Kwate Dassi L, Manica M, Probst D, Schwaller P, Nana Teukam YG, Laino T. Identification of Enzymatic Active Sites with Unsupervised Language Modeling. ChemRxiv. Cambridge: Cambridge Open Engage; 2021; This content is a preprint and has not been peer-reviewed. https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/61813dd08ac7a2b869651705/original/identification-of-enzymatic-active-sites-with-unsupervised-language-modeling.pdf

Semantic-Based self-Critical Training for Question Generation

Published in American Journal of Information Science and Technology, 2021

This paper is about building a language generation models to generate question which satisfy the standard of a semantic-based metric.

Recommended citation: Loïc Kwate Dassi, Semantic-Based Self-Critical Training for Question Generation, American Journal of Information Science and Technology. Volume 5, Issue 4, December 2021 , pp. 93-97. doi: 10.11648/j.ajist.20210504.12. http://www.ajist.org/article/526/10.11648.j.ajist.20210504.12

SISDH: A Model Based on SMAs and SIRs for the Simulation of the Evolution of COVID-19 in Cameroon

Published in World Journal of Engineering and Technology, 2021

This paper is about a model to simulate the evolution of COVID-19 in the Cameroonian context.

Recommended citation: Bernabe, B. , Esdras, F. , Brown, E. , Loïc, K. and Stephane, W. (2021) SISDH: A Model Based on SMAs and SIRs for the Simulation of the Evolution of COVID-19 in Cameroon. World Journal of Engineering and Technology, 9, 527-537. doi: [10.4236/wjet.2021.93035](10.4236/wjet.2021.93035). https://www.scirp.org/journal/paperinformation.aspx?paperid=111002

Computationally Accelerating Protein-Ligand Docking For Neglected Tropical Disease: A Study Case on Drug Repurposing For Leishmaniasis

Published in ICLR 2021 Machine Learning for Combating Pandemics Workshop, 2021

This paper is about building a language generation models to generate question which satisfy the standard of a semantic-based metric.

Recommended citation: Loic Dassi, Hassan Kane, and Ebenezer Nkwate. Computationally accelerating protein-ligand docking for neglected tropical diseases: A case study on drug repurposing for leishmaniasis. ICLR 2021 Workshop: Machine Learning for Preventing and Combating Pandemics, 2021. https://idl-bnc-idrc.dspacedirect.org/bitstream/handle/10625/60113/259fc522-d312-4c52-9438-d3257a7daa48.pdf?sequence=1