sif-embedding

This is currently a prototype version.

This is a Rust implementation of smooth inverse frequency (SIF) that is a simple but powerful embedding technique for sentences, described in the paper:

Sanjeev Arora, Yingyu Liang, and Tengyu Ma, A Simple but Tough-to-Beat Baseline for Sentence Embeddings, ICLR 2017.

Documentation

https://docs.rs/sif-embedding/

TODO

• [ ] Add the unsupervised SIF described in the paper.
• [ ] Support fastText models for word embeddings.
• [ ] Support serialization/deserialization of models.
• [ ] Provide Python binding
• [ ] Conduct more evaluations.

Evaluations

evaluations/semeval provides tools to evaluate sif-embedding on SemEval STS Task.

Wiki

Trouble shooting: Tips on how to resolve errors I faced in my environment.

Licensing

Licensed under either of

• Apache License, Version 2.0 (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0)
• MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT)

at your option.