Search Results for author:
Found 5 papers, 0 papers with code
SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach
We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model.
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
(2) how to predict a word via cloze test without knowing the number of wordpieces in advance?
Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model
Many downstream tasks and human readers rely on the output of the ASR system; therefore, errors introduced by the speaker and ASR system alike will be propagated to the next task in the pipeline.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders
However, the performance of using multiple encoders and decoders on zero-shot translation still lags behind universal NMT.
Improving Readability for Automatic Speech Recognition Transcription
In this work, we propose a novel NLP task called ASR post-processing for readability (APR) that aims to transform the noisy ASR output into a readable text for humans and downstream tasks while maintaining the semantic meaning of the speaker.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
