Limits...
Synonym set extraction from the biomedical literature by lexical pattern discovery.

McCrae J, Collier N - BMC Bioinformatics (2008)

Bottom Line: The assumption of extant resources such as parsers is also a limiting factor for many languages, so it is desirable to find patterns that do not use syntactical analysis.We conclude that automatic methods can play a practical role in developing new thesauri or expanding on existing ones, and this can be done with only a small amount of training data and no need for resources such as parsers.We also concluded that the accuracy can be improved by grouping into synonym sets.

View Article: PubMed Central - HTML - PubMed

Affiliation: National Institute of Informatics, Hitotsubashi 2-1-2, Chiyoda-ku, Tokyo, 101-8430, Japan. jmccrae@nii.ac.jp

ABSTRACT

Background: Although there are a large number of thesauri for the biomedical domain many of them lack coverage in terms and their variant forms. Automatic thesaurus construction based on patterns was first suggested by Hearst 1, but it is still not clear how to automatically construct such patterns for different semantic relations and domains. In particular it is not certain which patterns are useful for capturing synonymy. The assumption of extant resources such as parsers is also a limiting factor for many languages, so it is desirable to find patterns that do not use syntactical analysis. Finally to give a more consistent and applicable result it is desirable to use these patterns to form synonym sets in a sound way.

Results: We present a method that automatically generates regular expression patterns by expanding seed patterns in a heuristic search and then develops a feature vector based on the occurrence of term pairs in each developed pattern. This allows for a binary classifications of term pairs as synonymous or non-synonymous. We then model this result as a probability graph to find synonym sets, which is equivalent to the well-studied problem of finding an optimal set cover. We achieved 73.2% precision and 29.7% recall by our method, out-performing hand-made resources such as MeSH and Wikipedia.

Conclusion: We conclude that automatic methods can play a practical role in developing new thesauri or expanding on existing ones, and this can be done with only a small amount of training data and no need for resources such as parsers. We also concluded that the accuracy can be improved by grouping into synonym sets.

Show MeSH

Related in: MedlinePlus

Precision/Recall by Pattern. A scatter chart of precision vs recall for all generated patterns. Each point on this corresponds to a pattern generated from the test set and its recall and precision when used as the only variable for a classifier.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2335115&req=5

Figure 3: Precision/Recall by Pattern. A scatter chart of precision vs recall for all generated patterns. Each point on this corresponds to a pattern generated from the test set and its recall and precision when used as the only variable for a classifier.

Mentions: Table 3 lists the performance of some single patterns and gives us a baseline for our method and Figure 3 shows the spread of recall and precision for all generated patterns. It can be seen that most of these are variation on parentheses apposition patterns also suggested in Yu et al [12]. We also listed a number of patterns that were domain-specific, to show the value of generating patterns for each specific domain. Finally we examined three more patterns from Yu et al which did not perform so well in our experiments, this was partly due to our syntax-free approach matching sub-terms.


Synonym set extraction from the biomedical literature by lexical pattern discovery.

McCrae J, Collier N - BMC Bioinformatics (2008)

Precision/Recall by Pattern. A scatter chart of precision vs recall for all generated patterns. Each point on this corresponds to a pattern generated from the test set and its recall and precision when used as the only variable for a classifier.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2335115&req=5

Figure 3: Precision/Recall by Pattern. A scatter chart of precision vs recall for all generated patterns. Each point on this corresponds to a pattern generated from the test set and its recall and precision when used as the only variable for a classifier.
Mentions: Table 3 lists the performance of some single patterns and gives us a baseline for our method and Figure 3 shows the spread of recall and precision for all generated patterns. It can be seen that most of these are variation on parentheses apposition patterns also suggested in Yu et al [12]. We also listed a number of patterns that were domain-specific, to show the value of generating patterns for each specific domain. Finally we examined three more patterns from Yu et al which did not perform so well in our experiments, this was partly due to our syntax-free approach matching sub-terms.

Bottom Line: The assumption of extant resources such as parsers is also a limiting factor for many languages, so it is desirable to find patterns that do not use syntactical analysis.We conclude that automatic methods can play a practical role in developing new thesauri or expanding on existing ones, and this can be done with only a small amount of training data and no need for resources such as parsers.We also concluded that the accuracy can be improved by grouping into synonym sets.

View Article: PubMed Central - HTML - PubMed

Affiliation: National Institute of Informatics, Hitotsubashi 2-1-2, Chiyoda-ku, Tokyo, 101-8430, Japan. jmccrae@nii.ac.jp

ABSTRACT

Background: Although there are a large number of thesauri for the biomedical domain many of them lack coverage in terms and their variant forms. Automatic thesaurus construction based on patterns was first suggested by Hearst 1, but it is still not clear how to automatically construct such patterns for different semantic relations and domains. In particular it is not certain which patterns are useful for capturing synonymy. The assumption of extant resources such as parsers is also a limiting factor for many languages, so it is desirable to find patterns that do not use syntactical analysis. Finally to give a more consistent and applicable result it is desirable to use these patterns to form synonym sets in a sound way.

Results: We present a method that automatically generates regular expression patterns by expanding seed patterns in a heuristic search and then develops a feature vector based on the occurrence of term pairs in each developed pattern. This allows for a binary classifications of term pairs as synonymous or non-synonymous. We then model this result as a probability graph to find synonym sets, which is equivalent to the well-studied problem of finding an optimal set cover. We achieved 73.2% precision and 29.7% recall by our method, out-performing hand-made resources such as MeSH and Wikipedia.

Conclusion: We conclude that automatic methods can play a practical role in developing new thesauri or expanding on existing ones, and this can be done with only a small amount of training data and no need for resources such as parsers. We also concluded that the accuracy can be improved by grouping into synonym sets.

Show MeSH
Related in: MedlinePlus