Position-Invariant Truecasing with a Word-and-Character Hierarchical Recurrent Neural Network
Not on the map. Why?
Abstract (arXiv)
Truecasing is the task of restoring the correct case (uppercase or lowercase) of noisy text generated either by an automatic system for speech recognition or machine translation or by humans. It improves the performance of downstream NLP tasks such as named entity recognition and language modeling. We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network model, the first of its kind for this problem. Using sequence distillation, we also address the problem of truecasing while ignoring token positions in the sentence, i.e. in a position-invariant manner.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 10 of its 26 references that are in the map. First posted on arXiv 26 Aug 2021.
Builds on
10 of 26 references.
References · 10
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2016Sequence-Level Knowledge Distillationcited by 761
- 2019Corpora Generation for Grammatical Error Correctioncited by 53
- 2019Federated Learning of N-gram Language Modelscited by 33
- 2019Improving Performance of End-to-End ASR on Numeric Sequencescited by 17
- 2020Robust Prediction of Punctuation and Truecasing for Medical ASRcited by 16
- 2019Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Mergingcited by 14
- 2019Robust Named Entity Recognition with Truecasing Pretrainingcited by 11
- 2020An Efficient Architecture for Predicting the Case of Characters using Sequence Modelscited by 3
Built on by
Citing papers per year: 2022: 1.
1 paper.