Comments (5)
Thanks for posting this with the excellent details! This is quite interesting. I haven't noticed any strange effects with numbers, but haven't looked at them in detail. We aren't doing any special tokenization or normalization of numbers when training the model, and they are treated the same as all other tokens. When using datasets like Ontonotes we also just use the existing, provided tokenization.
Two questions:
- can you post an example of a few sentences from the dataset with these entity classes (e.g. ORDINAL, QUANTITY, DATE, etc)? This might help uncover the problem.
- have you tried the original ELMo model (not the 5.5B model) for this task? We haven't experimented with the 5.5B model too heavily, and it's possible this is a problem with the 5.5B model but not in the original model.
from bilm-tf.
Hi @kermitt2 -- just to follow up, we aren't able to reproduce these results on our end, and we are seeing improved performance with ELMo for all entity types in this dataset (including ORDINAL, etc). Perhaps it's something particular to how you are handling numbers vs strings in your pre-processing pipeline?
from bilm-tf.
Hello @matt-peters
Sorry for the late reply. The follow-up is super useful and I will revisit and double check my pre-processing given that it is thus coming from my side. The original ELMo model gave similar results for me. Many thanks!
from bilm-tf.
Just to close the loop on this, we saw a 0.882 development set F1 using the 5.5B ELMo model for this dataset (haven't checked the test set performance but it should be similar).
from bilm-tf.
Hey can you tell me where i can download the pretrained elmo ner ontonotes model. Thanks
from bilm-tf.
Related Issues (20)
- UnicodeError when run example: python -m unittest discover tests/ HOT 2
- how many time it takes if I training a 5GB corpus on 1080ti
- How to use ELMo in Keras version? HOT 1
- why should vocabulary file be sorted in descending order by token count in our training data๏ผ
- bug during data loading (and tests) HOT 2
- Training ELMO on TPU for generating embedding from custom dataset
- how to freeze some layers during training HOT 1
- Import Error: No module named bilm.training when I try to incrementally train ELMo HOT 1
- drastic impact of Changing the vocabulary on perplexity HOT 1
- incremental training on less than 2000 sentences HOT 2
- elmo sentence embeddings using usage_token.py
- The PyTorch version replication of the "Deep contextualized word representations" is missing
- Does any code about ELMO+ESIM? HOT 1
- Exporting finetuned model to SavedModel format for Tensorflow Serving HOT 6
- Compute training time
- Preparing training data for a domain with many multi keyword token HOT 1
- Running into error on tests HOT 3
- Saving the custom trained ELMO embedding (hdf5) in the format of tensorhub models
- 2021-10-29 14:13:30.313623: E C:\users\nwani\_bazel_nwani\mmtm6wb6\execroot\org_tensorflow\tensorflow\stream_executor\cuda\cuda_event.cc:49] Error polling for event status: failed to query event: CUDA_ERROR_OUT_OF_MEMORY
- Pre-trained links do not work HOT 7
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bilm-tf.