Comments (6)
I will push soon a model trained with fastText newest embeddings (trained on CommonCrawl). This way, you can use fastText feature for OOV words, and send the results embeddings to the InferSent encoder.
from infersent.
I was wondering about this as well.
One option would be to use dynamically generated word embeddings. Facebook also has its fastText project which can generate any OOV embedding because it trains and does inference on n-grams, not words. I think it wouldn't be necessary to retrain on your specific corpus this way. I plan to test the performance from replacing GloVe vectors with fastText.
from infersent.
I uploaded fastText model in 14b7ebb
I did not find the .bin for these vectors (crawl, https://fasttext.cc/docs/en/english-vectors.html) though, so not sure you will be able to encode the OOV words using the common-crawl English embeddings.
from infersent.
Unfortunately fastText does not provide the .bin for the English common-crawl word embeddings so handling OOV this way is not yet possible.
See facebookresearch/fastText#428 (comment)
from infersent.
@ncammarata: do you have concrete examples of entities from the dataset you use?
from infersent.
@aconneau hey sorry I missed this - I'm not working on a project that requires this anymore
from infersent.
Related Issues (20)
- Can not train from scratch? HOT 1
- link for the pre-trained models? HOT 2
- Decode sentence embedding to sentence HOT 1
- How can I train a model or modify the network to do it?
- adding train_nli back
- Error while loading the pretrained model HOT 1
- Usage on Google Collab HOT 2
- Same sentence, different encoding! HOT 1
- Can you save a model with vocab? HOT 1
- RuntimeError: [enforce fail at CPUAllocator.cpp:64] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 24776638464 bytes. Error code 12 (Cannot allocate memory)
- Cuda by Default
- Does this work anymore? HOT 2
- Vector Concatenation Question
- InferSent for Spanish
- ModuleNotFoundError: No module named 'models' HOT 1
- Infersent for Indian language
- How we fine tune inferSent for calassification problem like sentiment analysisi?
- KeyError: '</s>'
- extract features Infersent error HOT 1
- inconsistent sentences length causes encoding failure
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 infersent.