-
I think... Nori tokenizer has one issue.
I don’t understand why “Longest-Matching” is NOT working to Nori tokenizer via config mode (config mode:
Here is an example for explaining what is longe…
-
I think... Nori tokenizer has one issue.
I don’t understand why “Longest-Matching” is NOT working to Nori tokenizer via config mode (config mode:
Here is an example for explaining what is longe…
-
I am comparing the performance of the most popular lemmatization tools. I have found benchmark results for [Stanza](https://stanfordnlp.github.io/stanza/v100performance.html), [Trankit](https://tranki…
-
# Experiments design
Follow discussion [here](https://docs.google.com/document/d/110tlidAcpiNteKnA27tR5KPS_VahNqYKqCeJlu1MWww/edit#heading=h.wmf5tyes1tfk)
## pointers to code and datasets
### …
-
- [ ] Improve WordNet / Synonyms (NIKLex, KorLex)
- NIKLex : https://corpus.korean.go.kr/
- KorLex : http://korlex.pusan.ac.kr/
- [x] Improve README.md
~~docstring~~
- [x] requirements.txt ve…
-
## Environment info
- `transformers` version: 4.3.2
- Platform: Google Colab
- Python version: Python 3.7.12
- PyTorch version (GPU?): 1.8.0+cu111 (using Colab Pro - GPU/high-RAM)
- Tensorflo…
-
**Name of the Spark NLP feature whose docs need improvement:**
Linear Chain CRF
**What you think the docs should say:**
Hi, I want to thank you for this great NLP project first.
I am new to N…
-
pRO will be launching today for CBT let's all be updated for the new 3rd party programs we can use.... FF
-
Special Mission 3에서 언급된 `SparseRetrieval`와 `DenseRetrieval` 객체를 추상화시켜서 확장성있는 코드로 개발.
제공된 retrieval.py에는 boilerplate가 너무 많습니다.
이를 추상화시켜서 나중에 새로운 Retrieval를 추가해도 동작하도록 개발합니다.
+ End2End도 고민!
-
- [x] ec2 배포
- [x] 인덱스 매핑
- [x] 벌크로 더미 데이터 구축
- [x] 검색 테스트
- [ ] 데이터 싱크 전략 - #355
- [ ] 보안그룹 설정 - 특정 ip만 허용하도록 하고 추후 고도화 하기