Papers by Robert Bossy

3 papers
Bacteria Biotope at BioNLP Open Shared Tasks 2019 (D19-57)

Copied to clipboard

Challenge: The Bacteria Biotope task focuses on the extraction of the locations and phenotypes of microorganisms from PubMed abstracts and full-text excerpts.
Approach: They propose to use PubMed abstracts and full-text excerpts to extract the locations and phenotypes of microorganisms and to characterizations of these entities with respect to reference knowledge sources.
Outcome: The proposed subtasks, the corpus characteristics, and the challenge organization are compared with the previous edition in 2016 and the results are presented in the second edition.
SCoNE: a Self-Correcting and Noise-Augmented Method for Complex Biological and Chemical Named Entity Recognition (2026.eacl-long)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental task aimed at identifying entities such as names, locations, and organizations.
Approach: They propose a self-correcting and noise-augmented method for complex Biological and Chemical Named Entity Recognition that improves learning diversity and confidence.
Outcome: The proposed method outperforms baseline methods on CHEMDNER and microbial ecology datasets by 1.80 and 2.73 F1-scores.
Handling Entity Normalization with no Annotated Corpus: Weakly Supervised Methods Based on Distributional Representation and Ontological Information (2020.lrec-1)

Copied to clipboard

Challenge: Entity normalization is an important subtask of information extraction . it links entities mentions in text to categories or concepts in a reference vocabulary .
Approach: They propose a method that uses corpus selection, pre-processing and weak supervision strategies to address the scarcity of training data.
Outcome: The proposed method outperforms state-of-the-art methods in terms of accuracy and parametrization . it uses corpus selection, pre-processing and weak supervision strategies .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations