Comments (4)
I haven't done anything on this yet, I was planning to work on this on Thursday afternoon. But here's the new (empty) doc: https://docs.google.com/document/d/1kUJhoestVYged5gXfxS0fHeqZHkT_A1Q0pWnI_NRUs8/edit
from deezymatch.
Add the link to the HackMD file here once it is ready. That file can be used to capture comments from the participants. @mcollardanuy @fedenanni @kmcdono2 What do you think? We can then either ask participants to make issues directly on the repo (preferred) or add them to the HackMD file.
from deezymatch.
@kasra-hosseini et al do we need any introductory prose about the utility of DeezyMatch that goes beyond the current abstract/paper text? If so, happy to start thinking about this next week.
In the mean time @mcollardanuy if you need help with preparing the abstract to submit for Linked Pasts just say the word. Is there a google doc where I can add potential participants? Once the abstract is ready, we could email Bruno Martins and Paty Murrieta Flores about offering comment on the two aspects e.g. matching and gaz construction.
from deezymatch.
@kasra-hosseini et al do we need any introductory prose about the utility of DeezyMatch that goes beyond the current abstract/paper text? If so, happy to start thinking about this next week.
- We tried to cover most of DeezyMatch utilities in the abstract/paper. What do you think @mcollardanuy @fedenanni ? Maybe we can also mention that the length of the input strings can be changed (although it has not been tested on any realistic dataset)?
from deezymatch.
Related Issues (20)
- Improve documentation on DeezyMatch installation HOT 1
- Improve documentation on generating train/valid/test datasets HOT 4
- Test Tokenizer does not handle n-gram HOT 9
- Add specific datasets for the different DM functions and adapt test notebooks HOT 2
- Add option to extend the vocabulary when fine-tuning a model
- Add post-processing filter to candidate ranking with maximum string length difference allowed HOT 1
- Linting HOT 1
- Add OCR tutorial for DH2022
- Add Heritage Gazetteer of Libya tutorial for DH2022
- Query/Candidate matching on-the-fly
- Allow disabling cosine similarity in candidate ranking
- [Tutorials] Issue with pytorch GPU
- Scaling tests
- KeyError: 'general' | Can't train a model
- pip install deezymatch HOT 1
- Paper: Efficient Tokenization-Free Encoder
- Change package dependencies from == to >= HOT 2
- Fix ranking metric documentation in candidateRanker HOT 1
- Fix the hardcoded multiplier in candidateRanker HOT 1
- Improve documentation on string normalization HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deezymatch.