C-Norm: a neural approach to few-shot entity normalization

Abstract

Background Entity normalization is an important information extraction task which has gained renewed attention in the last decade, particularly in the biomedical and life science domains. In these domains, and more generally in all specialized domains, this task is still challenging for the latest machine learning-based approaches, which have difficulty handling highly multi-class and few-shot learning problems. To address this issue, we propose C-Norm, a new neural approach which synergistically combines standard and weak supervision, ontological knowledge integration and distributional semantics. Results Our approach greatly outperforms all methods evaluated on the Bacteria Biotope datasets of BioNLP Open Shared Tasks 2019, without integrating any manually-designed domain-specific rules. Conclusions Our results show that relatively shallow neural network methods can perform well in domains that present highly multi-class and few-shot learning problems.

TaeC: A manually annotated text dataset for trait and phenotype extraction and entity linking in wheat breeding literature

“…Named entity linking . Regarding the NEL evaluation, we assessed the performance of C-Norm [ 42 ] and BioSyn [ 45 ] for the prediction of trait and phenotype classes. We did not evaluate the prediction of species because the size of the NCBI taxonomy is beyond the capacity of the algorithms.…”

“…For the NEL task involving traits and phenotypes, we use the C-Norm and BioSyn algorithms. The C-Norm method [ 42 ] achieves state-of-the-art performance on the Bacteria Biotope dataset, which has good similarities to TaeC , i.e., deep ontology and complex entity terms. C-Norm represents terms in the texts using Word2vec embeddings [ 43 ], and it represents ontology classes using vectors that integrate hierarchical information from the ontology [ 44 ].…”

MilkOligoThesaurus, a dataset of mammalian milk oligosaccharide synonyms

“…Several strategies were developed and investigated to exploit external lexical and semantic resources to improve machine learning models. These strategies include thematic masking [1] , named entity recognition by distant supervision [2] , and ontology-based normalization [3] . The biological roles of MOs depend mainly on their structure.…”

A Rule-Based Approach to Embedding Techniques for Text Document Classification

“…INRA (Institut national de la recherche agronomique) and Cnrs (Centre national de la recherche scientifique) at University Paris Saclay proposed a two-step method to normalize multi-word terms with concepts from a domain-specific ontology. In this method, they used vector representations of terms computed with word embedding information and hierarchical information from ontology concepts [16]. Le and Mikolov presented word2vec and later introduced the doc2vec algorithm based on adjusted techniques for learning how to embed texts identical to word2vec, thus turning doc2vec into a branch of word2vec [17].…”