kampersanda / sif-embedding
Rust implementation of SIF and uSIF: Simple and fast sentence embedding
β19Updated 11 months ago
Related projects β
Alternatives and complementary repositories for sif-embedding
- Code for COLING 2020 Paperβ13Updated this week
- π A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure. (Python wrapper for daachorse)β15Updated last year
- β18Updated last month
- Utility scripts for preprocessing Wikipedia texts for NLPβ76Updated 7 months ago
- β24Updated this week
- π¦ Rust library of natural language dictionaries using character-wise double-array tries.β28Updated last year
- AllenNLP integration for Shiba: Japanese CANINE modelβ12Updated 3 years ago
- Finding all pairs of similar documents time- and memory-efficientlyβ58Updated 2 years ago
- A library for semantic similarity searchβ23Updated 2 months ago
- The evaluation scripts of JMTEB (Japanese Massive Text Embedding Benchmark)β33Updated this week
- Repository of ACL2023 paper: Unbalanced Optimal Transport for Unbalanced Word Alignmentβ36Updated last year
- β24Updated 2 years ago
- Funer is Rule based Named Entity Recognition tool.β22Updated 2 years ago
- FAST is an annotation tool that focuses on mobile devices. https://aclanthology.org/2021.emnlp-demo.41/β53Updated 3 years ago
- This repository has implementations of data augmentation for NLP for Japanese.β64Updated last year
- Training and evaluation scripts for JGLUE, a Japanese language understanding benchmarkβ17Updated this week
- β11Updated 2 months ago
- ζ¬θͺε€ζγΏγΉγ―γ«γγγθ©δΎ‘η¨γγΌγΏγ»γγβ20Updated last year
- Japanese synonym libraryβ52Updated 2 years ago
- Rust library providing fast language model queries in compressed spaceβ23Updated 2 years ago
- Codes to pre-train Japanese T5 modelsβ40Updated 3 years ago
- Yet another Python binding for Juman++/KNP/KWJAβ31Updated 3 weeks ago
- Annotated Fuman Kaitori Center Corpusβ17Updated 10 months ago
- Use custom tokenizers in spacy-transformersβ16Updated 2 years ago
- Yet another sentence-level tokenizer for the Japanese textβ22Updated 2 years ago
- β18Updated 5 months ago
- π₯ Vaporetto is a fast and lightweight pointwise prediction based tokenizer. This is a Python wrapper for Vaporetto.β20Updated 2 months ago
- Repository for JSICKβ44Updated last year
- DIRECT: Direct and Indirect REsponses in Conversational Text Corpusβ16Updated 3 years ago