prithivida
commited on
Commit
·
d3c1083
1
Parent(s):
15a97d2
Update README.md
Browse files
README.md
CHANGED
@@ -6,15 +6,17 @@ Parrot is a paraphrase based utterance augmentation framework purpose built to a
|
|
6 |
|
7 |
### Installation
|
8 |
```python
|
9 |
-
pip install
|
10 |
```
|
11 |
|
12 |
### Quickstart
|
13 |
```python
|
14 |
|
|
|
15 |
import warnings
|
16 |
warnings.filterwarnings("ignore")
|
17 |
-
|
|
|
18 |
phrases = ["Can you recommed some upscale restaurants in Rome?",
|
19 |
"What are the famous places we should not miss in Russia?"
|
20 |
]
|
@@ -60,7 +62,6 @@ Input_phrase: What are the famous places we should not miss in Russia
|
|
60 |
```python
|
61 |
|
62 |
para_phrases = parrot.augment(input_phrase=phrase,
|
63 |
-
diversity_ranker="levenshtein",
|
64 |
do_diverse=False,
|
65 |
max_return_phrases = 10,
|
66 |
max_length=32,
|
@@ -72,6 +73,7 @@ Input_phrase: What are the famous places we should not miss in Russia
|
|
72 |
|
73 |
|
74 |
|
|
|
75 |
## 2. Why Parrot?
|
76 |
**Huggingface** lists [12 paraphrase models,](https://huggingface.co/models?pipeline_tag=text2text-generation&search=paraphrase) **RapidAPI** lists 7 fremium and commercial paraphrasers like [QuillBot](https://rapidapi.com/search/paraphrase?section=apis&page=1), Rasa has discussed an experimental paraphraser for augmenting text data [here](https://forum.rasa.com/t/paraphrasing-for-nlu-data-augmentation-experimental/27744), Sentence-transfomers offers a [paraphrase mining utility](https://www.sbert.net/examples/applications/paraphrase-mining/README.html) and [NLPAug](https://github.com/makcedward/nlpaug) offers word level augmentation with a [PPDB](http://paraphrase.org/#/download) (a multi-million paraphrase database). While these attempts at paraphrasing are great, there are still some gaps and paraphrasing is NOT yet a mainstream option for text augmentation in building NLU models....Parrot is a humble attempt to fill some of these gaps.
|
77 |
|
|
|
6 |
|
7 |
### Installation
|
8 |
```python
|
9 |
+
pip install git+https://github.com/PrithivirajDamodaran/Parrot.git
|
10 |
```
|
11 |
|
12 |
### Quickstart
|
13 |
```python
|
14 |
|
15 |
+
from parrot import Parrot
|
16 |
import warnings
|
17 |
warnings.filterwarnings("ignore")
|
18 |
+
|
19 |
+
parrot = Parrot(diversity_ranker="euclidean", model_tag="prithivida/parrot_paraphraser_on_T5", use_gpu=False)
|
20 |
phrases = ["Can you recommed some upscale restaurants in Rome?",
|
21 |
"What are the famous places we should not miss in Russia?"
|
22 |
]
|
|
|
62 |
```python
|
63 |
|
64 |
para_phrases = parrot.augment(input_phrase=phrase,
|
|
|
65 |
do_diverse=False,
|
66 |
max_return_phrases = 10,
|
67 |
max_length=32,
|
|
|
73 |
|
74 |
|
75 |
|
76 |
+
|
77 |
## 2. Why Parrot?
|
78 |
**Huggingface** lists [12 paraphrase models,](https://huggingface.co/models?pipeline_tag=text2text-generation&search=paraphrase) **RapidAPI** lists 7 fremium and commercial paraphrasers like [QuillBot](https://rapidapi.com/search/paraphrase?section=apis&page=1), Rasa has discussed an experimental paraphraser for augmenting text data [here](https://forum.rasa.com/t/paraphrasing-for-nlu-data-augmentation-experimental/27744), Sentence-transfomers offers a [paraphrase mining utility](https://www.sbert.net/examples/applications/paraphrase-mining/README.html) and [NLPAug](https://github.com/makcedward/nlpaug) offers word level augmentation with a [PPDB](http://paraphrase.org/#/download) (a multi-million paraphrase database). While these attempts at paraphrasing are great, there are still some gaps and paraphrasing is NOT yet a mainstream option for text augmentation in building NLU models....Parrot is a humble attempt to fill some of these gaps.
|
79 |
|