-
## **Objetivo**
**Como** integrante do projeto Elmo
**Quero** alinhar estratégias juntamente com o restante da equipe
**Para** reduzir o tempo de tramitação dos processos
## **Contexto**
Atu…
-
### Metadata
- Authors: Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee and Luke Zettlemoyer
- Organization: Allen Institute for Artificial Intelligence
- …
-
Thank you for your excellent work and sharing code.
I tried retrain your model, perhaps because my experimental setting is not very appropriate, so I can't reproduce the results in the paper. The r…
-
Is it possible to use BERT word embeddings along with this NMT implementation?
The goal is to use a pre-trained BERT language model so the contextualized embedding could be leveraged.
I am wond…
-
To Do:
* . Use Stanford Contextualized Word Similarity
* Convert to tf_records using the existing dictionary so that the IDs match
* Split into validation and eval
Later:
* . Use ELMo eval m…
-
The setup steps are followed by the instruction from the documentation on ELMO's website. The procedures are tested working with the test drive server, but it fails with the one on AWS we setup.
Here …
-
Performances of two evaluation scripts differ as follows:
```
$ python evaluate.py $SQUAD_DEV_PATH /tmp/piqa/pred.json
{"exact_match": 52.81929990539262, "f1": 63.28879733489547}
$ python piqa_ev…
-
Hi, thanks for the very nice work.
I wonder if you will release the code for RL model?
-
Hi,
Really impressive work and a nice repository combining all the NER models.
I was trying to comprehend the codebase and what all are its capabilities. To that end, I made a list of NER-baselines …
-
In the development branch, I am unable to locate the issue why the logs for the development without docker and with docker are different. Here is the log when we start the development server without d…