Capitalization and punctuation restoration: a survey

V Păiş, D Tufiş - Artificial Intelligence Review, 2022 - Springer
Ensuring proper punctuation and letter casing is a key pre-processing step towards applying
complex natural language processing algorithms. This is especially significant for textual …

Multi-output RNN-T joint networks for multi-task learning of ASR and auxiliary tasks

W Wang, D Zhao, S Ding, H Zhang… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
We propose a multi-output joint network architecture for RNN-T transducer, for multi-task
modeling of ASR and auxiliary tasks that rely on ASR outputs. Each output of the joint …

Text Injection for Capitalization and Turn-Taking Prediction in Speech Models

S Bijwadia, S Chang, W Wang, Z Meng… - arXiv preprint arXiv …, 2023 - arxiv.org
Text injection for automatic speech recognition (ASR), wherein unpaired text-only data is
used to supplement paired audio-text data, has shown promising improvements for word …

Capitalization normalization for language modeling with an accurate and efficient hierarchical RNN model

H Zhang, YC Cheng, S Kumar… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Capitalization normalization (truecasing) is the task of restoring the correct case (uppercase
or lowercase) of noisy text. We propose a fast, accurate and compact two-level hierarchical …

The sentence end and punctuation prediction in nlg text (sepp-nlg) shared task 2021

D Tuggener, A Aghaebrahimian - Swiss Text Analytics …, 2021 - digitalcollection.zhaw.ch
This paper describes the first Sentence End and Punctuation Prediction in Natural
Language Generation (SEPP-NLG) shared task1 held at the SwissText conference 2021 …

Position-Invariant Truecasing with a Word-and-Character Hierarchical Recurrent Neural Network

H Zhang, YC Cheng, S Kumar, M Chen… - arXiv preprint arXiv …, 2021 - arxiv.org
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 …

Multilingual simultaneous sentence end and punctuation prediction

R Rei, F Batista, NM Guerreiro… - … sentence end and …, 2021 - repositorio.iscte-iul.pt
This paper describes the model and its corresponding setup, proposed by the Unbabel &
INESC-ID team for the 1st Shared Task on Sentence End and Punctuation Prediction in NLG …

The Impact of Offspring Hashtags on Semantic Polarization in Online Social Movements: Evidence from the Indian Farmer's Protest

RS Leekha - 2023 - vtechworks.lib.vt.edu
In this work, we investigate the role of offspring hashtags on the semantic polarization of
online discourse between the protest and counter-protest communities over time through the …

[PDF][PDF] NGHIÊ N CỨU PHƯƠNG PHÁP CHUẨN HOÁ VĂN BẢN VÀ NHẬN DẠNG THỰC THỂ ĐỊNH DANH TRONG NHẬN DẠNG TIẾNG NÓ I TIẾNG VIỆT

N HIỀN - 2023 - thuvienso.net
Luận án của tác giả được thực hiện tại Học viện Khoa học và Công nghệ-Viện Hàn lâm
Khoa học và Công nghệ Việt Nam, dưới sự hướng dẫn tận tình của PGS. TS. Lương Chi …

Fault Classification Method of Information System Based on Cascaded Convolutional Neural Network Model

R Ou, S Chen, L Qiao, Z Liu, X Cheng… - 2022 IEEE 5th …, 2022 - ieeexplore.ieee.org
Artificial intelligence plays an important role in data anomaly detection, which can
significantly improve the speed and accuracy of fault diagnosis and detection in power …