Repository navigation

Optimal_Transport_Aggregation_For_Robust_Textual_Descriptors

Public

About

This project enhances text encoders' global descriptors by implementing advanced aggregation techniques from computer vision literature, to improve sentence-level representations. We utilize models such as BERT, RoBERTa, and CLIP, and benchmark performance using datasets like MTEB, SemEval24 and Quora Question Pairs.

bert clip feature-aggregation roberta semantic-textual-similarity sinkhorn

0 stars

1 watching

Report repository

Name		Name	Last commit message	Last commit date
models		models
sentence_datasets		sentence_datasets
README.md		README.md
Report.pdf		Report.pdf
accelerate_config.yaml		accelerate_config.yaml
run.sh		run.sh
train.py		train.py

Repository files navigation

Optimal Transport Aggregation For Robust Textual Descriptors

Our presentation can be found here

Model checkpoints can be found here

About

This project enhances text encoders' global descriptors by implementing advanced aggregation techniques from computer vision literature, to improve sentence-level representations. We utilize models such as BERT, RoBERTa, and CLIP, and benchmark performance using datasets like MTEB, SemEval24 and Quora Question Pairs.

bert clip feature-aggregation roberta semantic-textual-similarity sinkhorn

0 stars

1 watching

Report repository

Contributors

Languages