Normalization of medical terms with multi-lingual resources

Patent metadata

Field	Value
Publication number	US-2021081502-A1
Application number	US-201916569874-A
Country	US
Kind code	A1
Filing date	Sep 13, 2019
Priority date	Sep 13, 2019
Publication date	Mar 18, 2021
Grant date	—

Abstract

Method and apparatus are presented for receiving a medical or medical condition related input term or phrase in a source language, and translating the term or phrase from the source language into at least one target language to obtain a set of translated terms of the input term. For each translated term in the set of translations, the method and apparatus further translate the set of translations back into the source language to obtain an output list of standard versions of the input term, scoring each entry of the output list as to probability of being the most standard version of the input term, and providing the entry of the output list that has the highest score to a user.

First claim

What is claimed is:

1 . A method comprising:
receiving a medical or medical condition related input term or descriptor in a source language; translating the term or descriptor from the source language into at least one target language to obtain a set of translated terms of the input term; for each translated term in the set of translations, translating the set of translations back into the source language to obtain an output list of standard versions of the input term; scoring each entry of the output list as to probability of being the most standard version of the input term; and providing the entry of the output list having the highest score to a user.

2 . The method of claim 1 , wherein the input term or descriptor is a common version of a medical concept, condition, object, process, or drug.

3 . The method of claim 1 , wherein each element of the set of translations is translated back into the source language using one or more pre-defined domain specific dictionaries.

4 . The method of claim 4 , wherein the one or more pre-defined domain specific dictionaries are professional, scientific or academic.

5 . The method of claim 1 , wherein the input term or descriptor is used in spoken Chinese.

6 . The method of claim 1 , wherein the at least one target language includes two separate target languages.

7 . The method of claim 6 , wherein the two separate target languages are each European languages.

8 . The method of claim 6 , wherein, for each of the two separate target languages a body of published medical literature exists.

9 . The method of claim 1 , further comprising outputting each entry of the output list, and its score, to the user.

10 . The method of claim 1 , wherein the score of each entry of the output list is determined by one or more of:
relative frequency of the entry in the source language, relative frequency of a term in the target language that was translated into the entry, or relative authority or prestige of the dictionary that was used to obtain the entry.

11 . A system, comprising:
an input interface configured to receive an input medical term or descriptor; an output interface; a medical term normalization engine coupled to the input interface and to the output interface, configured to:
convert the input medical term or descriptor into a standard or normalized equivalent via translation of the input term from its source language into a target language and re-translating from the target language back into the source language; and
output, via the output interface, one or more normalized terms corresponding to the medical term or descriptor.

12 . The system of claim 11 , the medical term normalization engine further comprising:
one or more first translators coupled to the input interface configured to generate translation results of the input medical term or descriptor into the target language; and a second translator configured to receive the translation results and re-translate them back into the source language using a professional or domain specific dictionary.

13 . The system of claim 12 , further comprising a search engine coupled to the one or more first translators and to the second translator, the search engine configured to find, from the output of each translator, one or more translation results to re-translate into the source language.

14 . The system of claim 11 , wherein there are two first translators, and wherein they are configured to operate in parallel to translate the input medical term or descriptor into each of two separate target languages.

15 . The system of claim 11 , further comprising a scoring engine configured to associate a probability score with each of the one or more normalized terms and to output the respective score for each of the one or more normalized terms.

16 . A computer program product for converting a common usage medical term into a standard or normalized equivalent, the computer program product comprising:
a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to: receive an medical or medical condition related input term or phrase in a source language; translate the term or phrase from the source language into at least one target language to obtain a set of translated terms of the input term; for each translated term in the set of translations:
translate the set of translations back into the source language to obtain an output list of standard versions of the input term; and
score each entry of the output list as to probability of being the most standard version of the input term; and
provide the entry of the output list having the highest score to a user.

17 . The computer program product of claim 11 , wherein the computer-readable program code is further executable to:
output each entry of the output list, and its score, to the user.

18 . The computer program product of claim 16 , wherein each element of the set of translations is translated back into the source language using one or more pre-defined domain specific dictionaries.

19 . The computer program product of claim 18 , wherein the one or more pre-defined domain specific dictionaries are professional, scientific or academic.

20 . The computer program product of claim 16 , wherein the score of each entry of the output list is determined by one or more of:
relative frequency of the entry in the source language, relative frequency of a term in the target language that was translated into the entry, or relative authority or prestige of the dictionary that was used to obtain the entry.

Assignees

• IBM

Inventors

• Jiang Jian Min
• Wang Jian
• Huang Songfang

Classifications

• G06F17/2288

  Physics · mapped topic

• G06F17/2818

  Physics · mapped topic

• G06F17/289 Primary

  Physics · mapped topic