NDLI: Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms

Please wait, while we are loading the content...

Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms

Content Provider	IEEE Xplore Digital Library
Author	Bicici, E. Yuret, D.
Copyright Year	2014
Abstract	We introduce FDA5 for efficient parameterization, optimization, and implementation of feature decay algorithms (FDA), a class of instance selection algorithms that use feature decay. FDA increase the diversity of the selected training set by devaluing features (i.e., n-grams) that have already been included. FDA5 decides which instances to select based on three functions used for initializing and decaying feature values and scaling sentence scores controlled with five parameters. We present optimization techniques that allow FDA5 to adapt these functions to in-domain and out-of-domain translation tasks for different language pairs. In a transductive learning setting, selection of training instances relevant to the test set can improve the final translation quality. In machine translation experiments performed on the 2 million sentence English-German section of the Europarl corpus, we show that a subset of the training set selected by FDA5 can gain up to 3.22 BLEU points compared to a randomly selected subset of the same size, can gain up to 0.41 BLEU points compared to using all of the available training data using only 15% of it, and can reach within 0.5 BLEU points to the full training set result by using only 2.7% of the full training data. FDA5 peaks at around 8M words or 15% of the full training set. In an active learning setting, FDA5 minimizes the human effort by identifying the most informative sentences for translation and FDA gains up to 0.45 BLEU points using 3/5 of the available training data compared to using all of it and 1.12 BLEU points compared to random training set. In translation tasks involving English and Turkish, a morphologically rich language, FDA5 can gain up to 11.52 BLEU points compared to a randomly selected subset of the same size, can achieve the same BLEU score using as little as 4% of the data compared to random instance selection, and can exceed the full dataset result by 0.78 BLEU points. FDA5 is able to reduce the time to build a statistical machine translation system to about half with 1M words using only 3% of the space for the phrase table and 8% of the overall space when compared with a baseline system using all of the training data available yet still obtain only 0.58 BLEU points difference with the baseline system in out-of-domain translation.
Starting Page	339
Ending Page	350
Page Count	12
File Size	1634393
File Format	PDF
ISSN	23299290
Volume Number	23
Issue Number	2
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-01-01
Publisher Place	U.S.A.
Access Restriction	One Nation One Subscription (ONOS)
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Training data Optimization IEEE transactions Speech Speech processing Adaptation models transductive learning Domain adaptation information retrieval instance selection machine translation
Content Type	Text
Resource Type	Article
Subject	Acoustics and Ultrasonics Signal Processing Instrumentation Speech and Hearing Electrical and Electronic Engineering Computational Mathematics 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

Optimizing instance selection for statistical machine translation with feature decay algorithms

Disambiguating Discourse Connectives for Statistical Machine Translation

Empirical use of information retrieval to build synthetic data for SMT domain adaptation

Exploring Diverse Features for Statistical Machine Translation Model Pruning

On the Evaluation of Adaptive Machine Translation for Human Post-Editing

Bilingual Continuous-Space Language Model Growing for Statistical Machine Translation

Multi-Feature Beat Tracking

Instance Selection for Machine Translation using Feature Decay Algorithms

Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors

Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms

Similar Documents

Optimizing instance selection for statistical machine translation with feature decay algorithms

Disambiguating Discourse Connectives for Statistical Machine Translation

Empirical use of information retrieval to build synthetic data for SMT domain adaptation

Exploring Diverse Features for Statistical Machine Translation Model Pruning

On the Evaluation of Adaptive Machine Translation for Human Post-Editing

Bilingual Continuous-Space Language Model Growing for Statistical Machine Translation

Multi-Feature Beat Tracking

Instance Selection for Machine Translation using Feature Decay Algorithms

Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors

Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms