Kun Han, Junwen Chen, HUI ZHANG, Haiyang Xu, Yiping Peng, Yun Wang, Ning Ding, Hui Deng, Yonghu Gao, Tingwei Guo, Yi Zhang, Yahao He, Baochang Ma, Yu-Long Zhou, Kangli Zhang, Chao Liu, Ying Lyu, Chenxi Wang, Cheng Gong, Yunbo Wang, Wei Zou, Hui Song, Xiangang Li
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Natural Language Inference | SNLI | % Test Accuracy | 80.7 | DELTA (LSTM) |
| Slot Filling | ATIS | F1 | 0.952 | DELTA (BLSTM-CRF) |
| Intent Detection | ATIS | Accuracy | 97.4 | DELTA (BLSTM-CRF) |
| Text Summarization | CNN / Daily Mail | ROUGE-L | 27.3 | DELTA (BLSTM) |
| Text Classification | TREC-6 | Error | 7.8 | DELTA (CNN) |
| Text Classification | Yahoo! Answers | Accuracy | 75.1 | DELTA (HAN) |
| Abstractive Text Summarization | CNN / Daily Mail | ROUGE-L | 27.3 | DELTA (BLSTM) |
| Classification | TREC-6 | Error | 7.8 | DELTA (CNN) |
| Classification | Yahoo! Answers | Accuracy | 75.1 | DELTA (HAN) |