Comments (2)
Hi @LivingScripts, do you mean that you have a pre-trained NER model with N entities and want to train it further, with new data and M new entities, so that it will recognize M+N entities?
If so, NLP Architect supports only training models from scratch, meaning, you'll have to train a new model with all the data you have (old+new).
Even if NLP Architect will support such scenario (of an additional train phase), you will probably deal with catastrophic forgetting (the model will start to forget things it learned from the old data and might fail to classify old data correctly). For that purpose, you'll have to use all the data you have in training.
from nlp-architect.
exactly what I was after, thanks
from nlp-architect.
Related Issues (20)
- question: How can i use the Topic and Trend Analysis Solution HOT 1
- How to improve bist model accuracy? :Bistmodel HOT 6
- Terms file is empty, no terms to re-rank HOT 1
- dimension error HOT 1
- url for quant BERT config.json is invalid HOT 1
- bug: [an error occurred while running Q8BERT] HOT 3
- bug: [In ABSA Opinion lixicon and Aspect lexicon are not being written to a csv when you run train.py] HOT 4
- bug: ABSA: Passing spacy_model="fr_core_news_sm" to SentimentInference gives an error HOT 2
- question: [Evaluation results of the Q8BERT] HOT 2
- Problem with installing nlp-architect in google-colab HOT 2
- bug: [Memory error while training the absa solution model] HOT 3
- bug: Couldn't reach server for bert-base-uncased model URL HOT 1
- bug: zipfile.BadZipFile using pretrained BIST model HOT 4
- improvement: distillation for TransformerSequenceClassifier models for GLUE tasks
- question: [Q8Bert experiment Setting] HOT 2
- question: [Quantization] Which files to change to make inference faster for Q8BERT? HOT 1
- bug: ERROR: ResolutionImpossible
- Why the number of data from restaurant and laptop is different from the paper?
- question: [question topic]
- Performance issue in the definition of _inference, examples/memn2n_dialogue/memn2n_dialogue.py(P1) HOT 2
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 nlp-architect.