Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Extraction for Thai text #304

Merged
merged 2 commits into from
Oct 16, 2024
Merged

Extraction for Thai text #304

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
46829e3
add thai stopwords
sarahyurick Oct 15, 2024
1b0e7a4
run black
sarahyurick Oct 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions nemo_curator/download/commoncrawl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,6 +224,11 @@ def get_stop_list_dict(languages=[]):
lang_key = language.upper()
stop_list_dict[lang_key] = justext.get_stoplist(language)

# List obtained from https://github.com/stopwords-iso/stopwords-th
from .thai_stopwords import thai_stopwords

stop_list_dict["THAI"] = thai_stopwords

return stop_list_dict


Expand Down
119 changes: 119 additions & 0 deletions nemo_curator/download/thai_stopwords.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,119 @@
thai_stopwords = frozenset(
[
"กล่าว",
"กว่า",
"กัน",
"กับ",
"การ",
"ก็",
"ก่อน",
"ขณะ",
"ขอ",
"ของ",
"ขึ้น",
"คง",
"ครั้ง",
"ความ",
"คือ",
"จะ",
"จัด",
"จาก",
"จึง",
"ช่วง",
"ซึ่ง",
"ดัง",
"ด้วย",
"ด้าน",
"ตั้ง",
"ตั้งแต่",
"ตาม",
"ต่อ",
"ต่าง",
"ต่างๆ",
"ต้อง",
"ถึง",
"ถูก",
"ถ้า",
"ทั้ง",
"ทั้งนี้",
"ทาง",
"ทำ",
"ทำให้",
"ที่",
"ที่สุด",
"ทุก",
"นอกจาก",
"นัก",
"นั้น",
"นำ",
"นี้",
"น่า",
"บาง",
"ผล",
"ผ่าน",
"พบ",
"พร้อม",
"มา",
"มาก",
"มี",
"ยัง",
"รวม",
"ระหว่าง",
"รับ",
"ราย",
"ร่วม",
"ลง",
"วัน",
"ว่า",
"สำหรับ",
"สุด",
"ส่ง",
"ส่วน",
"หนึ่ง",
"หรือ",
"หลัง",
"หลังจาก",
"หลาย",
"หาก",
"อยาก",
"อยู่",
"อย่าง",
"ออก",
"อะไร",
"อาจ",
"อีก",
"เขา",
"เข้า",
"เคย",
"เฉพาะ",
"เช่น",
"เดียว",
"เดียวกัน",
"เนื่องจาก",
"เปิด",
"เปิดเผย",
"เป็น",
"เป็นการ",
"เพราะ",
"เพื่อ",
"เมื่อ",
"เรา",
"เริ่ม",
"เลย",
"เห็น",
"เอง",
"แต่",
"แบบ",
"แรก",
"และ",
"แล้ว",
"แห่ง",
"โดย",
"ใน",
"ให้",
"ได้",
"ไป",
"ไม่",
"ไว้",
]
)