-
```
The stanford classifier uses an NERClassifierCombiner.
This is absent from the Stanford Module.
This becomes problematic when using the coreference resolver.
What version of the product are you …
-
**Is your feature request related to a problem? Please describe.**
Calculation of the CEAF evaluation metric for coreference can be very slow, especially when there is a sparse contingency matrix (li…
-
## Context
Observed high latency due to GPT. There are two instances where GPT is utilized.
1) Coref
2) Formatting of answers
This can cause frustration to user while waiting for the respons…
-
I'm reading Clark and Manning (2016) and the list of features include "String Matching Features: Head match, exact string match, and partial string match."
I look at [datasets.py](https://github.co…
-
Hi, @juntaoy
Not sure it is the place to ask or not. I'm reading the paper [Multi-task Learning Based Neural Bridging Reference Resolution](https://arxiv.org/abs/2003.03666) and the code for this …
ghost updated
4 years ago
-
running `make conll` produces
/tmp/dg/maz-1423.mmax_only.conll
```
1 Die _ _ _ _ _ _ _ _ _ _ _ _ (6
2 Diskussion _ _ _ _ _ _ _ _ _ _ _ _ 6)
3 ,…
-
I am having some problems when running the script. I created my environment using the muda_env.yml file. When I test it on a small test document, I run into a "coref error". It seems to me that it is …
-
From the `xcomp` guidelines:
> An open clausal complement (`xcomp`) of a verb or an adjective is a predicative or clausal complement without its own subject. The reference of the subject is necessari…
-
I tried training the coreference model (using the instructions in the README), but the training job was killed due to infra issues after the training for 17 full epochs (out of 19 requested epochs).
…
-
```
The stanford classifier uses an NERClassifierCombiner.
This is absent from the Stanford Module.
This becomes problematic when using the coreference resolver.
What version of the product are you …