Comments (5)
As for any other model in pytorch you can do .cuda()
from genre.
Dear Nicola,
Thank you for your response and interesting work. We are struggling to reproduce your results. Can you please share your evaluation code and also all the changes that affect the results, but have been included in this repository (e.g., the changes you mentioned in your response)?
I guess there should not be IP/copyright issues to share your evaluation code and GERBIL middleware, right?
from genre.
Hi!
If you can run the example, there is no problem with your GENRE setting AFAIK. The problem is in the setting:
- as you can see from the examples we have a setting where we use a
mention_trie
and amention_to_candidates_dict
. I used them as not empty for the experiments in the paper. In particular, I used the entity universe from https://github.com/dalab/end2end_neural_el and the same from the mapping from mention to candidates. I also did some filerting (e.g., since the task is named entity linking and not entity linking in general, I removed all mentions that do not start with a capital letter). - I did not use the function
get_entity_spans
for evaluating with GERBIL. That function was added in the repo afterwards to demonstrate how to get predictions using GENRE. For instance, that function does not handle splitting the input into chunks when is too long which is needed for evaluating properly (since BART can handle at most 1024 tokens). I also had to modify some code (from https://github.com/dalab/end2end_neural_el and the GERBIL repository for enabling having the middleware and unfortunately we cannot release that code).
I hope this is helfpul.
from genre.
Thank you very much for your detailed answer. It is very clear.
Could I also ask about the question 2 above: Is there any setting to allow the GPU to be used for inference? (By default, GPU is not used for inference, right?)
from genre.
Thanks!
from genre.
Related Issues (20)
- is prefix_allowed_tokens_fn only working for seq2seq model.generate? HOT 2
- Loading mgenre models is taking 44GB RAM
- Problem in candidate-based generation on GENRE using transformers >= 4.36.0 HOT 1
- the same entity name question
- Inference speed is too slow. Is this problem because of Constrained beam search?
- can not receive different outputs from mGENRE.sample using dropout in train mode and different seeds HOT 2
- can't find ID to title map json file HOT 1
- alignment between candidate and KILT wikipedia data source HOT 4
- Question: Running genre on multiple GPUs HOT 1
- format of entries for entity linking training HOT 2
- Invalid prediction - no wikipedia entity HOT 10
- Fail to Reproduce the dev score of GENRE Document Retrieval HOT 7
- mGENRE finetuning issue
- Why do you prepend `eos_token_id' to sent_orig HOT 2
- colab script to run GENRE
- NameError: name 'batched_hypos' is not defined (mGENRE) HOT 5
- [Question] Evaluating mGENRE on Mewsli-9
- Fine-tune with hugging face trainer
- import package error
- Chinese entity linking
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 genre.