ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision

Abstract

Scientific literature analysis needs fine-grained named entity recognition (NER) to provide a wide range of information for scientific discovery. For example, chemistry research needs to study dozens to hundreds of distinct, fine-grained entity types, making consistent and accurate annotation difficult even for crowds of domain experts. On the other hand, domain-specific ontologies and knowledge bases (KBs) can be easily accessed, constructed, or integrated, which makes distant supervision realistic for fine-grained chemistry NER. In distant supervision, training labels are generated by matching mentions in a document with the concepts in the knowledge bases (KBs). However, this kind of KB-matching suffers from two major challenges: incomplete annotation and noisy annotation. We propose CHEMNER, an ontologyguided, distantly-supervised method for finegrained chemistry NER to tackle these challenges. It leverages the chemistry type ontology structure to generate distant labels with novel methods of flexible KB-matching and ontology-guided multi-type disambiguation. It significantly improves the distant label generation for the subsequent sequence labeling model training. We also provide an expertlabeled, chemistry NER dataset with 62 finegrained chemistry types (e.g., chemical compounds and chemical reactions). Experimental results show that CHEMNER is highly effective, outperforming substantially the stateof-the-art NER methods (with .25 absolute F1 score improvement).

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.…”

Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge

“…Distant supervision (Mintz et al, 2009) uses structured knowledge to annotate raw text with pseudo labels. Performing distantly supervised fine-tuning with in-domain structured knowledge after the MLM pre-training is effective in domainspecific NER (Wang et al, 2021;Trieu et al, 2022). However, domain-specific distant supervised learning depends on the structured knowledge's coverage of the label set of the downstream task.…”

Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains

“…(3) Experiments: Extensive experiments on two public datasets (Tabassum et al 2020;Bridges et al 2013) covering four domains (i.e., StackOverflow, GitHub, National Vulnerability Database, and Metasploit) demonstrate the effectiveness of SETYPE given 10 to 15 fine-grained types related to code, software, and security. Although we focus on software and security domain examples, our entity typing framework can be applied to other specialized domains including science (Wang et al 2021) and engineering (O'Gorman et al 2021).…”