Comments (5)
from bert_score.
Thank you for using our BERTScore.
The reason for this error is that both BERT and RoBERTa are trained with sentences with at most 512 tokens. Unlike the original Transformers, BERT and RoBERTa use learned positional embedding whose size is set during training.
BERTScore is commonly computed between a pair of sentences.
We would suggest that you split the documents into sentences before feeding them to BERT.
If there happen to be some sentences with more than 512 tokens, you can:
- train a BERT model using longer sentences
- cut sentences into multiple chunks and design a better way to aggregate them. This is one of the future directions to extend BERTScore, but we haven't studied it yet.
- use XLNets which support longer inputs. However, they perform worse in our experiments.
Best,
Felix
from bert_score.
Will if work will it for sentence having length > 512, I remove stopwords and common words?
from bert_score.
But BERT as a service allows user to make max_sequence= ignore
Can't we do something with that?
https://github.com/hanxiao/bert-as-service
from bert_score.
As far as I know, they just trim down the sequence. Please see:
https://github.com/hanxiao/bert-as-service/blob/85690491d66fd1ca0d03924f8c9ead3d1cad90b1/server/bert_serving/server/__init__.py#L414-L422
We would like to follow huggingface's transformers and just raise an error instead.
We encourage users to deal with their own special cases.
Thank you for raising this issue. We will update the README to remind other users.
from bert_score.
Related Issues (20)
- BERTScore complexity ? HOT 2
- Use fine tuned model HOT 6
- get_wmt18_seg_result question HOT 3
- exception when passing numpy arrays as inputs HOT 1
- requests.exceptions.ProxyError: HTTPSConnectionPool(host='huggingface.co', port=443) HOT 2
- inputs format & running warning HOT 1
- Different roberta-large results with transformers>=4.17.0 HOT 1
- will bert-score cli command automatically use gpu? how? HOT 1
- Could you please add some models for Ukrainian language? HOT 4
- Bertscore not working for Hindi language
- A negative rescaled value HOT 10
- a little difference in results. HOT 3
- RuntimeError when using bert-base-chinese offline HOT 1
- Warning HOT 1
- BERTScore with covid-twitter-bert
- Padding token ID HOT 2
- Run bert_score on TPU (google colab) instead of gpu.
- Calculate embeddings once HOT 1
- Tensor size error with multiple refs tweets
- Can bertscore calculate semantic similarity between languages?
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 bert_score.