NDLI: Exponential language modeling using morphological features and multi-task learning

Content Provider	ACM Digital Library
Author	Pierrehumbert, Janet Fang, Hao Baumann, Peter Ostendorf, Mari
Copyright Year	2016
Abstract	For languages with fast vocabulary growth and limited resources, data sparsity leads to challenges in training a language model. One strategy for addressing this problem is to leverage morphological structure as features in the model. This paper explores different uses of unsupervised morphological features in both the history and prediction space for three word-based exponential models (maximum entropy, logbilinear, and recurrent neural net (RNN)). Multi-task training is introduced as a regularizing mechanism to improve performance in the continuous-space approaches. The models are compared to non-parametric baselines. From using the RNN with morphological features and multi-task learning, experiments with conversational speech from four languages show we can obtain consistent gains of 7-11% in perplexity reduction in a limited-resource scenario (10 hrs speech), and 12-18% when the training size is increased (80 hrs). Results are mixed for all other approaches, compared to a modified Kneser-Ney baseline, but morphology is useful in continuous-space models compared to their word-only baseline. Multi-task learning improves both continuous-space models.
Starting Page	2410
Ending Page	2421
Page Count	12
File Format	PDF
ISSN	23299290
e-ISSN	23299304
DOI	10.1109/TASLP.2015.2482118
Volume Number	23
Issue Number	12
Journal	IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-12-01
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Language model Limited resources Morphology Neural network
Content Type	Text
Resource Type	Article
Subject	Instrumentation Computational Mathematics Signal Processing Electrical and Electronic Engineering Acoustics and Ultrasonics Speech and Hearing Media Technology

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Exponential Language Modeling Using Morphological Features and Multi-Task Learning

Extractive broadcast news summarization leveraging recurrent neural network language modeling techniques

Regression-based context-dependent modeling of deep neural networks for speech recognition

Converting Neural Network Language Models into Back-off Language Models for Efficient Decoding in Automatic Speech Recognition

A sparse plus low-rank exponential language model for limited resource scenarios

Extractive Broadcast News Summarization Leveraging Recurrent Neural Network Language Modeling Techniques

Two efficient lattice rescoring methods using recurrent neural network language models

Syntactic and semantic features for code-switching factored language models

Adaptive multi-compositionality for recursive neural network models

Exponential language modeling using morphological features and multi-task learning

Similar Documents

Exponential Language Modeling Using Morphological Features and Multi-Task Learning

Extractive broadcast news summarization leveraging recurrent neural network language modeling techniques

Regression-based context-dependent modeling of deep neural networks for speech recognition

Converting Neural Network Language Models into Back-off Language Models for Efficient Decoding in Automatic Speech Recognition

A sparse plus low-rank exponential language model for limited resource scenarios

Extractive Broadcast News Summarization Leveraging Recurrent Neural Network Language Modeling Techniques

Two efficient lattice rescoring methods using recurrent neural network language models

Syntactic and semantic features for code-switching factored language models

Adaptive multi-compositionality for recursive neural network models

Exponential language modeling using morphological features and multi-task learning