SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.09207 · NeurIPS · 2023

RETVec: Resilient and Efficient Text Vectorizer

Elie Bursztein, Marina Zhang, Owen Vallis, Xinyu Jia

arXiv · PDF · Open in the Atlas

Code that ran

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.

RepositoryRoleRan
google-research/retvec canonical 3 of 7
FunctionStatusWhere 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")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

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.