Feature engineering for MEDLINE citation categorization with MeSH

Background Research in biomedical text categorization has mostly used the bag-of-words representation. Other more sophisticated representations of text based on syntactic, semantic and argumentative properties have been less studied. In this paper, we evaluate the impact of different text representa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:BMC bioinformatics Ročník 16; číslo 1; s. 113
Hlavní autoři: Jimeno Yepes, Antonio Jose, Plaza, Laura, Carrillo-de-Albornoz, Jorge, Mork, James G, Aronson, Alan R
Médium: Journal Article
Jazyk:angličtina
Vydáno: London BioMed Central 08.04.2015
BioMed Central Ltd
Témata:
Abstracting and Indexing as Topic - methods
Algorithms
Analysis
Artificial Intelligence
Bioinformatics
Biomedical and Life Sciences
Comparative analysis
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Data mining
Humans
Information Storage and Retrieval
Knowledge-based analysis
Life Sciences
Medical Subject Headings
MEDLINE
Microarrays
Research Article
Semantics
MeSH indexing
Text categorization
Feature engineering
Biomedical literature
ISSN:1471-2105, 1471-2105
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Background Research in biomedical text categorization has mostly used the bag-of-words representation. Other more sophisticated representations of text based on syntactic, semantic and argumentative properties have been less studied. In this paper, we evaluate the impact of different text representations of biomedical texts as features for reproducing the MeSH annotations of some of the most frequent MeSH headings. In addition to unigrams and bigrams, these features include noun phrases, citation meta-data, citation structure, and semantic annotation of the citations. Results Traditional features like unigrams and bigrams exhibit strong performance compared to other feature sets. Little or no improvement is obtained when using meta-data or citation structure. Noun phrases are too sparse and thus have lower performance compared to more traditional features. Conceptual annotation of the texts by MetaMap shows similar performance compared to unigrams, but adding concepts from the UMLS taxonomy does not improve the performance of using only mapped concepts. The combination of all the features performs largely better than any individual feature set considered. In addition, this combination improves the performance of a state-of-the-art MeSH indexer. Concerning the machine learning algorithms, we find that those that are more resilient to class imbalance largely obtain better performance. Conclusions We conclude that even though traditional features such as unigrams and bigrams have strong performance compared to other features, it is possible to combine them to effectively improve the performance of the bag-of-words representation. We have also found that the combination of the learning algorithm and feature sets has an influence in the overall performance of the system. Moreover, using learning algorithms resilient to class imbalance largely improves performance. However, when using a large set of features, consideration needs to be taken with algorithms due to the risk of over-fitting. Specific combinations of learning algorithms and features for individual MeSH headings could further increase the performance of an indexing system.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-015-0539-7