Bidirectional Recurrent Neural Network with Attention Mechanism for Punctuation Restoration

被引：111

作者：

Tilk, Ottokar ^{[1
]}

Alumae, Tanel ^{[2
]}

机构：

[1] Tallinn Univ Technol, Inst Cybernet, Tallinn, Estonia

[2] Raytheon BBN Technol, Cambridge, MA USA

来源：

17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES | 2016年

关键词：

neural network; punctuation restoration; CAPITALIZATION;

D O I：

10.21437/Interspeech.2016-1517

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Automatic speech recognition systems generally produce unpunctuated text which is difficult to read for humans and degrades the performance of many downstream machine processing tasks. This paper introduces a bidirectional recurrent neural network model with attention mechanism for punctuation restoration in unsegmented text. The model can utilize long contexts in both directions and direct attention where necessary enabling it to outperform previous state-of-the-art on English (IWSLT2011) and Estonian datasets by a large margin.

引用

页码：3047 / 3051

页数：5

共 50 条

[1] Punctuation Restoration for Ukrainian Broadcast Speech Recognition System based on Bidirectional Recurrent Neural Network and Word Embeddings
Sazhok, Mykola
Poltieva, Anna
Robeiko, Valentyna
Seliukh, Ruslan
Fedoryn, Dmytro
COLINS 2021: COMPUTATIONAL LINGUISTICS AND INTELLIGENT SYSTEMS, VOL I, 2021, 2870
[2] Optical Proximity Correction Using Bidirectional Recurrent Neural Network With Attention Mechanism
Kwon, Yonghwi
Shin, Youngsoo
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2021, 34 (02) : 168 - 176
[3] Punctuation Prediction using a Bidirectional Recurrent Neural Network with Part-of-Speech Tagging
Juin, Chin Char
Wei, Richard Xiong Jun
D'Haro, Luis Fernando
Banchs, Rafael E.
TENCON 2017 - 2017 IEEE REGION 10 CONFERENCE, 2017, : 1806 - 1811
[4] Comparison of Recurrent Neural Networks for Slovak Punctuation Restoration
Hladek, Daniel
Stas, Jan
Ondas, Stanislav
2019 10TH IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFOCOMMUNICATIONS (COGINFOCOM 2019), 2019, : 95 - 99
[5] Self-Attention Based Network for Punctuation Restoration
Wang, Feng
Chen, Wei
Yang, Zhen
Xu, Bo
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 2803 - 2808
[6] Bidirectional LSTM for Automatic Punctuation Restoration
Salimbajevs, Askars
HUMAN LANGUAGE TECHNOLOGIES - THE BALTIC PERSPECTIVE, 2016, 289 : 59 - 65
[7] Recurrent neural network with attention mechanism for language model
Chen, Mu-Yen
Chiang, Hsiu-Sen
Sangaiah, Arun Kumar
Hsieh, Tsung-Che
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (12): : 7915 - 7923
[8] Recurrent neural network with attention mechanism for language model
Mu-Yen Chen
Hsiu-Sen Chiang
Arun Kumar Sangaiah
Tsung-Che Hsieh
Neural Computing and Applications, 2020, 32 : 7915 - 7923
[9] Attention-Based Convolution Bidirectional Recurrent Neural Network for Sentiment Analysis
Sivakumar, Soubraylu
Haritha, D.
Ram, Sree N.
Kumar, Naveen
Krishna, Rama G.
Kumar, Dinesh A.
INTERNATIONAL JOURNAL OF DECISION SUPPORT SYSTEM TECHNOLOGY, 2022, 14 (01)
[10] Gesture Class Prediction by Recurrent Neural Network and Attention Mechanism
Yunus, Fajrian
Clavel, Chloe
Pelachaud, Catherine
PROCEEDINGS OF THE 19TH ACM INTERNATIONAL CONFERENCE ON INTELLIGENT VIRTUAL AGENTS (IVA' 19), 2019, : 233 - 235

← 1 2 3 4 5 →