Comments (2)
inukshuk
commented on June 10, 2024
1
I think this is very much a factor of the variety of your data. For the parser model, I'd guess that a model trained on about 50 references should already be OK in many cases. For a long time our default model was trained on less than 500 and with 500-1,500 I've experienced the best results myself.
For the finder model we have 15 ttx files in the repo; the default model is trained on an additional 40 files (including books and dissertations with multiple chapters).
from anystyle.
Mkranj
commented on June 10, 2024
Thank you very much, that's a lot of help :)
from anystyle.
Related Issues (20)
- Add stripping of "by ..." to names normalizer HOT 1
- how can I make my gem installed version behave like the online anystyle.io HOT 5
- Anystyle "doing nothing". HOT 1
- anystyle find: File name too long @ rb_sysopen HOT 1
- Move CI to GitHub
- References in Danish (or other languages?) HOT 2
- ttx parser breaks if line doesn't end with space HOT 5
- pdftotext not found HOT 2
- Question: training different types of "ref" HOT 1
- Tokenizer doesn't parse Volume/issue typeset with no space. HOT 3
- Include Roman numerals in pages in Bibtex output
- training finder with xml documents HOT 10
- Input count wrong: limit yourself to 1000 references per request HOT 4
- Error: uninitialized constant AnyStyle::ParserCore::StringUtils in Ruby 3.2.2 HOT 4
- Consider normalizing whitespace HOT 3
- Is it possible to delete characters/words when editing the parsed citation? HOT 3
- Error collecting references from a pdf HOT 3
- Getting a 500 Internal Server Error HOT 5
- Reference not parsing for this Chinese Character 著 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 anystyle.