Elie Bursztein, Marina Zhang, Owen Vallis, Xinyu Jia
We lifted 7 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| google-research/retvec | canonical | 3 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| RETVecIntToBinary | Ran | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("1953f86b2e83d02f") |
| RETVecIntegerizer | Ran | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("776e1afaf9b7c7da") |
| _reshape_embeddings | Ran | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("8bb9169209b09470") |
| RETVecBinarizer | Not yet run | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("bde2b45305369264") |
| RETVecEmbedding | Not yet run | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("97997be5edd715b5") |
| RETVecTokenizer | Not yet run | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("27a5474470da210f") |
| download_retvec_saved_model | Not yet run | google-research/retvec/retvec/tf/layers/tokenizer.py code served (permissive licence) · get_code("0fa9283e2d6d503d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper describes RETVec, an efficient, resilient, and multilingual text vectorizer designed for neural-based text processing. RETVec combines a novel character encoding with an optional small embedding model to embed words into a 256-dimensional vector space. The RETVec embedding model is pretrained using pair-wise metric learning to be robust against typos and characterlevel adversarial attacks. In this paper, we evaluate and compare RETVec to state-of-the-art vectorizers and word embeddings on popular model architectures and datasets. These comparisons demonstrate that RETVec leads to competitive, multilingual models that are significantly more resilient to typos and adversarial text attacks. RETVec is available under the Apache 2 license at https://github.com/google-research/retvec.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.09207")
get_code_for_paper("2302.09207")
have("2302.09207")
Connect an agent — have() is free.