Skip to main content

Table 2 List of studies presented in this review categorized by NLP method used and language(s) addressed

From: Clinical Natural Language Processing in languages other than English: opportunities and challenges

Method/Task

Language/reference cited in this review

Core NLP

 

- Morphology

FR [78] PL [29]

- Part of Speech tagging

PT [28] ES [30]

- Parsing

FI [32, 38, 40] FR [31, 77] GR [52] JA [33, 37]

- Segmentation

DE [27] HE [41]

Resource development

 

- Lexicons

BG [62] EL [52] EU [51] FR [50, 6567] HE [44] JA [49] SV[48] ZH [68, 69]

- Corpora and annotation

EL [52] EN-{FR,ES} [54] EN-{ES,FR,PT} [55]

 

ES [58] FR [59, 117]

- Models, methods

DE [53] FR [60]

De-identification

FR [56, 79, 89, 90] KO [91] SV [57, 92]

Information extraction

 

- Medical Concepts

BG [62, 64] ZH [42, 43] DE [80, 84, 115, 124] DU [114] ES [34]

 

IT [46, 47, 97] PL [82] SV [61]

- Findings/Symptoms

DE [118], SV [61, 93] ZH [96]

- Drugs/Adverse events

BG [95, 102] DA [87] ES [98] FR [94, 116] SV [61]

- Specific characteristics

EN-{ZH,FR,DE,JA,ES} [154] FR [120] ZH [99] DU [114]

- Relations

BG [64] DE [84, 115] IT [46, 47]

Classification

 

- Phenotyping from EHR text

BG [100] ES [119] FI [121] FR [7, 126] KA [125] PT [83]

 

SV [123] ZH [122]

- Indexing and coding

EN-FR [71] FI [85] FR [153] JA [149, 151]

- Patient-authored text

JA [127]

- Cohort stratification

DA [86] DE [88]

Context Analysis

DU [110]

- Negation detection

BG [101] DA [45] DE [106] DU [110] ES [107, 108]

 

FR,DE,SV [109] SV [104, 105]

- Uncertainty/Assertion

SV [105] ZH [103]

- Temporality

FR [112] SV [113]

- Abbreviation

DE [36] SV [35]

- Experiencer

DU [110]

Multilingual tasks

 

- Translation

EN-ES [157] EN-FR [159] EN-{KO,RU,ES,ZH} [155]

 

EN-{FR,DE,HU,PL,ES,TU} [156], FR-DE [158]

- Information Retrieval

AR [162] FR [160], EN-{CZ,DE,FR} [163] EN-{ES,FR} [161]

- Cultural analysis

DE [72], EN-ZH [73], FI-SV [74]

Shared tasks

 

- CLEF-ER2013

DE,DU,FR,ES- [138]

- CLEF eHealth 2015, 2016

FR [152, 153]

- NTCIR 2014, 2016

JA [149, 151]

  1. The two letter language codes are introduced in Table 1. When multiples languages are addressed in one paper we provide a comma separated list; dashes mark language pairs in multilingual work