Leader: Prefixing a Length for Faster Word Vector Serialization
원문 초록
Two competing file formats have become the de facto standards for distributing pre-trained word embeddings. Both are named after the most popular pre-trained embeddings that are distributed in that format. The GloVe format is an entirely text based format that suffers from huge file sizes and slow reads, and the word2vec format is a smaller binary format that mixes a textual representation of words with a binary representation of the vectors themselves. Both formats have problems that we solve with a new format we call the Leader format. We include a word length prefix for faster reads while maintaining the smaller file size a binary format offers. We also created a minimalist library to facilitate the reading and writing of various word vector formats, as well as tools for converting pre-trained embeddings to our new Leader format.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
A Comparative Analysis of Static Word Embeddings for Hungarian
Geological Inference from Textual Data using Word Embeddings
Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work
Comply: Learning Sentences with Complex Weights inspired by Fruit Fly Olfaction
QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.