-
# Feature description
## Current behavior
Currently task related messages (task creation, errors, result, events) are not name-spaced.
This results in all agents (workers) receiving all messag…
-
In this step, we address the challenge of incorporating underrepresented languages with a focus on low-resource languages. This effort confronts the prevalent imbalance in NLP systems, which are predo…
-
Dataloader name: `uit_viquad/uit_viquad.py`
DataCatalogue: http://seacrowd.github.io/seacrowd-catalogue/card.html?uit_viquad
| Dataset| uit_viquad |
|-------------|---|
| Description | Vietnamese…
-
Some strings make the annotate function crash:
```python
import spacy
from spacy.matcher import PhraseMatcher
# load default skills data base
from skillNer.general_params import SKILL_DB
# i…
-
Possible convo including the NLP Turing group?
Would like to discuss
- low resource NLP tools, how these can be developed with humanities (e.g. cultural expertise) input
- historical languages that…
-
The following papers help guide our work. The techniques and experiments we hope to leverage for our study are well explained in these papers.
- [[2307.16833] Data Augmentation for Neural Machine Tra…
-
My specs are:
```
GPU 0: NVIDIA A100-PCIE-40GB
MEM: 60 GB
```
My config file looks like:
```
model:
arch: video_llama
model_type: pretrain_vicuna
freeze_vit: True
freeze_qformer…
-
السلام عليكم ورحمة الله وبركاته
ممكن ترشيحات افكار او مواضيع جديده فى arabic NLP for research (for master students)
-
# Dialect-to-Standard Normalization
The goal of this task is to evaluate to what extent speech models encode dialectal variation, by prompting models to normalize dialectal variants of Swiss German…
-
# Guest lecture @ UNC Charlotte: Labeling with LLMs
A few weeks ago, I held a guest lecture at University of North Carolina Charlotte on how we can use large language models for annotation in the con…