Pzoom522/xANLG
Data and code for "Understanding Linearity of Cross-Lingual Word Embedding Mappings" (TMLR 2022)
This project offers data and code to evaluate how well word meanings translate across different languages using mathematical models. It takes pre-trained word embeddings for various languages as input and checks if a simple linear transformation can accurately map words from one language to another. Researchers and computational linguists studying multilingual natural language processing (NLP) would find this useful.
No commits in the last 6 months.
Use this if you are a researcher in natural language processing and need to test the linearity of cross-lingual word embedding mappings for your linguistic analysis.
Not ideal if you are looking for a ready-to-use tool to perform cross-lingual text analysis or machine translation without a research focus.
Stars
12
Forks
1
Language
Python
License
AGPL-3.0
Category
Last pushed
Jun 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Pzoom522/xANLG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ymcui/cmrc2018
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
thunlp/MultiRD
Code and data of the AAAI-20 paper "Multi-channel Reverse Dictionary Model"
princeton-nlp/DensePhrases
[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval...
IndexFziQ/KMRC-Papers
A list of recent papers regarding knowledge-based machine reading comprehension.
danqi/rc-cnn-dailymail
CNN/Daily Mail Reading Comprehension Task