R
Rao Ma
Researcher at Shanghai Jiao Tong University
Publications - 19
Citations - 127
Rao Ma is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 4, co-authored 13 publications receiving 52 citations.
Papers
More filters
Posted Content
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
TL;DR: A two-stage semantic parsing framework, where the first stage utilizes an unsupervised paraphrase model to convert an unlabeled natural language utterance into the canonical utterance and the downstream naive semantic parser accepts the intermediate output and returns the target logical form.
Proceedings ArticleDOI
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
TL;DR: The authors proposed a two-stage semantic parsing framework, where the first stage utilizes an unsupervised paraphrase model to convert an unlabeled natural language utterance into the canonical utterance.
Proceedings ArticleDOI
AISpeech-SJTU ASR System for the Accented English Speech Recognition Challenge
TL;DR: AISpeech-SJTU ASR system for the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC) as mentioned in this paper achieved the second position in the challenge with a word error rate of 4.00% on dev set and 4.47% on test set.
Proceedings ArticleDOI
AISpeech-SJTU Accent Identification System for the Accented English Speech Recognition Challenge
TL;DR: The AISpeech-SJTU system for the accent identification track of the Interspeech 2020 Accented English Speech Recognition Challenge as mentioned in this paper achieved the best accuracy of 83.63% on the challenge evaluation data.
Journal ArticleDOI
Neural Network Language Model Compression With Product Quantization and Soft Binarization
Kai Yu,Rao Ma,Kaiyu Shi,Qi Liu +3 more
TL;DR: Two recently proposed quantization approaches, product quantization (PQ) and soft binarization are effectively combined to address the issue of large memory consumption of the neural network language models.