-
Hello,
Just wanted to confirm if the whole CoreNLP based in Java is being converted to neural based in Python? If so, any idea when this is expected to be ready?
I love the Stanza Python suppo…
-
I simply want to use state of the art coreference resolution.
it should take an arbitrary input text made of valid english and output the resolutions of pronouns.
How can I achieve this basic usage …
-
I am using the finetuned checkpoint of unilm-v1 for squad question generation task that's provided here https://github.com/microsoft/unilm/tree/master/unilm-v1
Since the model, it's trained on is -…
ghost updated
4 years ago
-
## 概要
- 既存のTransformerは入力系列長に応じてO(N^2)で計算量が増加するためO(N)でスケールできるようにする
- Sliding window attention, Dilated sliding window, Global+sliding windowなどを使用し、必要ないAttentionの計算を省く
- text8、enwik8でSoTA、長い文書ではRoBE…
reo11 updated
4 years ago
-
Rebecca - Russian + toxicology
@rimusa - Spanish + toxicology
@pandyamugdha - English + toxicology
We need to assign who is using which English + downstream task (coref, toxicity) and what tool…
-
Hello there, my name is Martin, I'm currently working with your api and I found the following bug:
When trying to solve a coreference using the "coreference resolution" with the text:
"Mary has bl…
-
I am developing an Android application (I am a beginner). I want to use Stanford CoreNPL 3.8.0 library in my app to extract the part of speech, the lemma, the parser and so on from the user sentences.…
-
**Describe the bug**
I have an allennlp virt env and have allennlp installed successfully. I am able to use the dep parse predictor perfectly for analysis, but when I use the coref predictor via the…
-
Wikipedia dataset for word embeddings
This should be a group decision as well for the two people who work on English, and can be decided independently for the other language. This is extremely flex…
-
Hi,
I tried to run the code and got this error:
```
RuntimeError: unexpected EOF, expected 10413410 more bytes. The file might be corrupted.
terminate called after throwing an instance of 'c10::Er…