diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-04-03 15:16:17 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-04-03 15:16:17 -0700 |
| commit | fb767adb9472ff85b46b5a383f3986950b12dd27 (patch) | |
| tree | 724af4412353c627b0eae26fd4d7fd1164bf2b55 /notes | |
| parent | 4cbbdf33ee2a9651f79f96e4bf290d8bc721f69d (diff) | |
| download | fatcat-covid19-fb767adb9472ff85b46b5a383f3986950b12dd27.tar.gz fatcat-covid19-fb767adb9472ff85b46b5a383f3986950b12dd27.zip | |
move more directories around
Diffstat (limited to 'notes')
| -rw-r--r-- | notes/fulltext_search.md | 3 | ||||
| -rw-r--r-- | notes/machine_translation.md | 22 |
2 files changed, 25 insertions, 0 deletions
diff --git a/notes/fulltext_search.md b/notes/fulltext_search.md new file mode 100644 index 0000000..938abff --- /dev/null +++ b/notes/fulltext_search.md @@ -0,0 +1,3 @@ + +https://ambar.cloud/blog/2016/11/24/es-hl-large-docs/ +https://ambar.cloud/blog/2017/01/02/es-large-text/ diff --git a/notes/machine_translation.md b/notes/machine_translation.md new file mode 100644 index 0000000..519f0c1 --- /dev/null +++ b/notes/machine_translation.md @@ -0,0 +1,22 @@ + +Overall concept is to use machine translation to fill gaps or provide a +starting point for human translation. Quality would obviously be best from +experience human translators with domain knowledge. + +Ideas: +- translate GROBID XML or JSON output offline +- call a platform/API to translate individual papers +- can directly link to google translate (or other platform) of the paper + +## Free Software + +NiuTrans: Chinese-to-english focus, C++ + +Apertium: popular, but no Chinese? + +Moses: no Chinese examples? + + +## Platforms + +Google Translate |