mira/bertalign
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
bfsujason
2022-04-17 00:18:37 +08:00
committed by GitHub
parent 2abc392518
commit 60521ee4d0
1 changed files with 0 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -24,8 +24,6 @@ Alignment between 25 languages: Catalan (ca), Chinese (zh), Czech (cs), Danish (
Please see [requirements.txt](./requirements.txt) for installation information. If you are running Bertalign on *GPU-enabled Linux* such as Google Colaboratory, please install *faiss-gpu* for faster processing. Please see [requirements.txt](./requirements.txt) for installation information. If you are running Bertalign on *GPU-enabled Linux* such as Google Colaboratory, please install *faiss-gpu* for faster processing.
---
##### Basic example ##### Basic example
Just import *Bertalign* and initialize it with the source and target text, which will detect the source and target language automatically and split both texts into sentences. Then invoke the method *align_sents()* to align sentences and print out the result with *print_sents()*. Just import *Bertalign* and initialize it with the source and target text, which will detect the source and target language automatically and split both texts into sentences. Then invoke the method *align_sents()* to align sentences and print out the result with *print_sents()*.
@@ -242,8 +240,6 @@ log_final_scores(scores)
Bertalign is released under the [GNU General Public License v3.0](./LICENCE) Bertalign is released under the [GNU General Public License v3.0](./LICENCE)
---
##### Credits ##### Credits
###### Main Libraries ###### Main Libraries
@@ -262,8 +258,6 @@ Bertalign is released under the [GNU General Public License v3.0](./LICENCE)
* [Vecalign](https://github.com/thompsonb/vecalign) * [Vecalign](https://github.com/thompsonb/vecalign)
---
##### Todo List ##### Todo List
- Try the [CNN model](https://tfhub.dev/google/universal-sentence-encoder-multilingual/3) for sentence embeddings - Try the [CNN model](https://tfhub.dev/google/universal-sentence-encoder-multilingual/3) for sentence embeddings