DELTA: A DEep learning based Language Technology plAtform

Kun Han, Junwen Chen, Hui Zhang, Haiyang Xu, Yiping Peng +18 more
8/2/2019
cs.CLcs.LG

Official code: Delta-ML/delta (1,608 stars, Apache-2.0, TensorFlow, last commit 2025-04-16).

Abstract

In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network models for training as well as comprehensive deployment tools for production. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. We demonstrate the reliable performance with DELTA on several natural language processing and speech tasks, including text classification, named entity recognition, natural language inference, speech recognition, speaker verification, etc. DELTA has been used for developing several state-of-the-art algorithms for publications and delivering real production to serve millions of users.

View on arXivView PDF

Code Implementations(1)

Delta-ML/deltaOfficial100%
TensorFlowApache-2.0

DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/

1,608281C, GoMay 29, 20191 years agoApache-2.0
asrcustom-opsdeep-learningemotion-recognitionfront-end+15 more

Similar Papers

Cite this paper

@article{han2019delta,
  title  = {DELTA: A DEep learning based Language Technology plAtform},
  author = {Kun Han and Junwen Chen and Hui Zhang and Haiyang Xu and Yiping Peng and Yun Wang and Ning Ding and Hui Deng and Yonghu Gao and Tingwei Guo and Yi Zhang and Yahao He and Baochang Ma and Yulong Zhou and Kangli Zhang and Chao Liu and Ying Lyu and Chenxi Wang and Cheng Gong and Yunbo Wang and Wei Zou and Hui Song and Xiangang Li},
  year   = {2019},
  eprint = {1908.01853},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1908.01853}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1908.01853.svg)](https://codeofpaper.com/paper/1908.01853)

Discussion