Comments (3)
Thanks for pointing this out!
I re-wrote augment_sentence
and expand_tokens
indexing the nodes by integers (their positions in the augmentations
list) instead of spans. The root is now -1. This implementation should be cleaner, as it clearly distinguishes between the root and an entity that spans the whole sentence.
from tanl.
Hi, you are right. Thanks for spotting the problem and providing a simple solution!
from tanl.
Hi,
I just found that my solution above is incomplete. There also have to be changes made in expand_tokens
to recover the index from -1 to 0. To be more specific, I add
i = max(i, 0)
above line 39 and
start = max(start, 0)
before line 45 in utils.py
.
I am sorry for not fully testing my solution before posting.
Best,
Xiang
from tanl.
Related Issues (12)
- About performance on tacred HOT 3
- The format of Multiwoz dataset HOT 7
- Episode numbers in few-shot experiment HOT 3
- About the training batch size used in the low resource experiments HOT 2
- About data files used for the FewRel dataset HOT 1
- Ace2005EventExtraction Dataset HOT 1
- CoNLL2012 Datasets in .json format HOT 1
- ATIS and SNIPS Dataset Source HOT 3
- reproduce on other datasets
- How to save tokenizer automatically? HOT 1
- Inquiry Regarding ACE2005-Event Data for TANL
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 tanl.