tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect

SetFit Aspect Model with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification. In particular, this model is in charge of filtering aspect span candidates.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

This model was trained within the context of a larger system for ABSA, which looks like so:

1. Use a spaCy model to select possible aspect span candidates.
2. Use this SetFit model to filter these possible aspect span candidates.
3. Use a SetFit model to classify the filtered aspect span candidates.

Model Details

Model Description

• Model Type: SetFit
• Sentence Transformer body: sentence-transformers/paraphrase-mpnet-base-v2
• Classification head: a LogisticRegression instance
• spaCy Model: en_core_web_lg
• SetFitABSA Aspect Model: tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect
• SetFitABSA Polarity Model: tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity
• Maximum Sequence Length: 512 tokens
• Number of Classes: 2 classes

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Label	Examples
aspect	'staff:But the staff was so horrible to us.' "food:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora." "food:The food is uniformly exceptional, with a very capable kitchen which will proudly whip up whatever you feel like eating, whether it's on the menu or not."
no aspect	"factor:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora." "deficiencies:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora." "Teodora:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora."

Evaluation

Metrics

Label	Accuracy
all	0.8780

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import AbsaModel

# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
    "tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect",
    "tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	17.9296	37

Label	Training Sample Count
no aspect	71
aspect	128

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 16)
• max_steps: -1
• sampling_strategy: oversampling
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0007	1	0.3388	-
0.0370	50	0.2649	-
0.0740	100	0.1562	-
0.1109	150	0.1072	-
0.1479	200	0.0021	-
0.1849	250	0.0007	-
0.2219	300	0.0008	-
0.2589	350	0.0003	-
0.2959	400	0.0002	-
0.3328	450	0.0003	-
0.3698	500	0.0002	-
0.4068	550	0.0001	-
0.4438	600	0.0001	-
0.4808	650	0.0001	-
0.5178	700	0.0001	-
0.5547	750	0.0001	-
0.5917	800	0.0001	-
0.6287	850	0.0002	-
0.6657	900	0.0001	-
0.7027	950	0.0001	-
0.7396	1000	0.0001	-
0.7766	1050	0.0001	-
0.8136	1100	0.0001	-
0.8506	1150	0.0001	-
0.8876	1200	0.0001	-
0.9246	1250	0.0001	-
0.9615	1300	0.0001	-
0.9985	1350	0.0	-

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.009 kg of CO2
• Hours Used: 0.111 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.9.16
• SetFit: 1.0.0.dev0
• Sentence Transformers: 2.2.2
• spaCy: 3.7.2
• Transformers: 4.29.0
• PyTorch: 1.13.1+cu117
• Datasets: 2.15.0
• Tokenizers: 0.13.3

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}