-
My understanding is that fine-tuning using sentence-transformers over pairs assumes that the pairs are symmetric.
For example, using [ContrastiveTensionLossInBatchNegatives](https://sbert.net/docs/pa…
-
Single quotes need to be identified and isolated from apostrophes. They can be replaced with the appropriate Unicode single quote characters, while apostrophes can remain the apostrophe character (or …
-
这是我的程序
```
import tornado.ioloop
import tornado.web
import tornado.httpserver
import json
import tornado.options
from tornado.options import define, options
from BCEmbedding import RerankerMod…
-
Let's say you have per class 10 examples of sentences and want to use a loss where you expect a sentence pair like for MultipleNegativesRankingLoss. This expects positive sentence pairs. So, is it act…
-
**Paper**
Noising and Denoising Natural Language: Diverse Back Translation for Grammar Correction
**Introduction**
This research proposes a solution for data sparsity (noisy and clean pairs) in g…
-
I'm trying to batch add sentence and I'm getting the following `Error: 'word_color'`. I edited the python a little and found that if I initialize the config_data object, I don't get that error. I'm un…
-
# Overview
Add data transformation/cleaning to the XRI script outlined in the parent issue: https://github.com/sillsdev/silnlp/issues/472
# Background
The creation of an initial script was ca…
-
Hi I would like to contribute a Pulaar translator model, but need pointed to the the sentence pairs. Can anyone help me out?
-
# Sentence Grammar Acceptability
## Task Objective
The task is to verify whether the model understands English grammar (i.e., understands syntax) by evaluating on a task that determine whether a g…
-
Traceback (most recent call last):
File "/home/xzhou/paper-baseline/AncSetfit-main/train.py", line 3, in
from setfit.modeling import SetFitBaseModel, SKLearnWrapper, sentence_pairs_generation…