Improving methods for normalizing biomedical text entities with concepts from an ontology with (almost) no training data at BLAH5 the CONTES

다국어 초록 (Multilingual Abstract)

Entity normalization, or entity linking in the general domain, is an information extraction task that aims to annotate/bind multiple words/expressions in raw text with semantic references, such as concepts of an ontology. An ontology consists minimally of a formally organized vocabulary or hierarchy of terms, which captures knowledge of a domain. Presently, machine-learning methods, often coupled with distributional representations, achieve good performance. However, these require large training datasets, which are not always available, especially for tasks in specialized domains. CONTES (CONcept-TErm System) is a supervised method that addresses entity normalization with ontology concepts using small training datasets. CONTES has some limitations, such as it does not scale well with very large ontologies, it tends to overgeneralize predictions, and it lacks valid representations for the out-of-vocabulary words. Here, we propose to assess different methods to reduce the dimensionality in the representation of the ontology. We also propose to calibrate parameters in order to make the predictions more accurate, and to address the problem of out-of-vocabulary words, with a specific method.

참고문헌 (Reference)

1 Grover A, "node2vec: scalable feature learning for networks" Association for Computing Machinery 855-864, 2016

2 Jurafsky D, "Speech and Language Processing" Prentice-Hall Inc 2014

3 Ferre A, "Representation of complex terms in a vector space structured by an ontology for a normalization task" Association for Computational Linguistics 99-106, 2017

4 Deleger L, "Overview of the bacteria biotope task at BioNLP Shared Task 2016" Association for Computational Linguistics 12-22, 2016

5 Morgan AA, "Overview of BioCreative II gene normalization" 9 (9): S3-, 2008

6 Sil A, "Neural cross-lingual entity linking" University of Edinburgh

7 Bojanowski P, "Enriching word vectors with subword information" 5 : 135-146, 2017

8 Mikolov T, "Efficient estimation of word representations in vector space" Cornell University

9 LeCun Y, "Deep learning" 521 : 436-444, 2015

10 Craven M, "Constructing biological knowledge bases by extracting information from text sources" 77-86, 1999

11 Ferre A, "Combining rule-based and embedding-based approaches to normalize textual entities with an ontology" European Languages Resources Association

12 Cohen KB, "Biomedical Natural Language Processing" John Benjamins Publishing Company 2014

13 Wang JZ, "A new method to measure the semantic similarity of GO terms" 23 : 1274-1281, 2007