EMPIRICAL METHODS FOR SPLITTING COMPOUND WORDS WITH APPLICATION TO MACHINE TRANSLATION

Patent №

US 7,711,545

Granted

2010-05-04

Filed 2004

Owner

SOUTHERN CALIFORNIA, UNIVERSITY OF

Lab

—

AI components

ml · nlp · speech · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10884174

A statistical machine translation (MT) system may include a compound splitting module to split compounded words for more accurate translation. The compound splitting module select a best split for translation by the MT system.

Machine learning Natural language Speech Knowledge representation AI hardwareG06F 40/268G06F 40/44

Google Patents

AI classification

Natural language1.00

Machine learning1.00

Speech1.00

Knowledge representation0.95

AI hardware0.85

Planning0.01

Evolutionary computation0.00

Vision0.00

Ownership

SOUTHERN CALIFORNIA, UNIVERSITY OF

assignment · 152620916

Assignors

KOEHN, PHILIPP

On an employer assignment, the assignors are typically the inventors.

From the same owner

SELECTION AND USE OF NONSTATISTICAL TRANSLATION COMPONENTS IN A STATISTICAL MACHINE TRANSLATION FRAMEWORKUS 8,666,725 · 2014 IMAGE ENCODING/DECODING SYSTEM USING GRAPH BASED PIXEL PREDICTION AND ENCODING SYSTEM AND METHODUS 8,554,001 · 2013 PREPARING AND PRESENTING CONTENTUS 8,250,073 · 2012 SYNTAX-BASED STATISTICAL TRANSLATION MODELUS 8,214,196 · 2012 3D FACE RECONSTRUCTION FROM 2D IMAGESUS 8,126,261 · 2012 METHODS FOR FAST PROGRESSIVE EVALUATION OF POLYNOMIAL RANGE-SUM QUERIES ON REAL-TIME DATACUBESUS 8,090,730 · 2012 TENSOR VOTING IN N DIMENSIONAL SPACESUS 7,953,675 · 2011 SYSTEM AND METHOD FOR AUTOMATIC ROOM ACOUSTIC CORRECTION IN MULTI-CHANNEL AUDIO ENVIRONMENTSUS 7,769,183 · 2010

Cites (53)

METHOD AND APPARATUS FOR PROVIDING STOCHASTIC FINITE-STATE MACHINE TRANSLATIONUS 7,113,903 · 2006 DETERMINING A COMPACT MODEL TO TRANSCRIBE THE ARABIC LANGUAGE ACOUSTICALLY IN A WELL DEFINED BASIC PHONETIC STUDYUS 7,107,215 · 2006 SYSTEM AND INTERATIVE METHOD FOR LEXICON, SEGMENTATION AND LANGUAGE MODEL JOINT OPTIMIZATIONUS 6,904,402 · 2005 HIERARCHICAL LANGUAGE CHUNKING TRANSLATION TABLEUS 6,782,356 · 2004 COMPRESSION METHOD,METHOD FOR COMPRESSING ENTRY WORD INDEX DATA FOR A DICTIONARY, AND MACHINE TRANSLATION SYSTEMUS 6,502,064 · 2002 METHOD, SYSTEM AND COMPUTER PROGRAM PRODUCT FOR AUTOMATIC CHARACTER TRANSLITERATION IN A TEXT STRING OBJECTUS 6,460,015 · 2002 SYSTEM AND METHOD FOR IDENTIFYING LANGUAGE USING MORPHOLOGICALLY-BASED TECHNIQUESUS 6,415,250 · 2002 USING RANKED TRANSLATION CHOICES TO OBTAIN SEQUENCES INDICATING MEANINGS OF MULTI-TOKEN EXPRESSIONSUS 6,393,389 · 2002 METHOD AND APPARATUS FOR MULTI-LANGUAGE INDEXINGUS 6,389,387 · 2002 METHOD OF AND APPARATUS FOR RETRIEVING INFORMATION AND STORAGE MEDIUMUS 6,360,196 · 2002 SYSTEM FOR CHINESE TOKENIZATION AND NAMED ENTITY RECOGNITIONUS 6,311,152 · 2001 CHINESE GENERATION APPARATUS FOR MACHINE TRANSLATION TO CONVERT A DEPENDENCY STRUCTURE OF A CHINESE SENTENCE INTO A CHINESE SENTENCEUS 6,289,302 · 2001 SYSTEM AND METHOD FOR ESTIMATING ACCURACY OF AN AUTOMATIC NATURAL LANGUAGE TRANSLATIONUS 6,285,978 · 2001 AUTOMATED SYSTEM FOR GENERATING NATURAL LANGUAGE TRANSLATIONS THAT ARE DOMAIN-SPECIFIC, GRAMMAR RULE-BASED, AND/OR BASED ON PART-OF-SPEECH ANALYSISUS 6,278,967 · 2001 METHOD AND SYSTEM FOR EXTRACTING PAIRS OF MULTILINGUAL TERMINOLOGY FROM AN ALIGNED MULTILINGUAL TEXT.US 6,236,958 · 2001 METHOD AND APPARATUS FOR PARSING IN A SPOKEN LANGUAGE TRANSLATION SYSTEMUS 6,223,150 · 2001 SUMMARIZATION APPARATUS AND METHODUS 6,205,456 · 2001 METHOD AND SYSTEM FOR OPTIMIZING LOGISTICAL OPERATIONS IN LAND SEISMIC SURVEYSUS 6,182,014 · 2001 TRANSLATION METHOD AND SYSTEMUS 6,182,027 · 2001 MACHINE ASSISTED TRANSLATION TOOLS UTILIZED AN INVERTED INDEX AND LIST OF LETTER N-GRAMSUS 6,131,082 · 2000 TRANSLATION MACHINE WITH FORMAT CONTROLUS 6,119,077 · 2000 STATISTICAL TRANSLATION SYSTEM AND METHOD FOR FAST SENSE DISAMBIGUATION AND TRANSLATION OF LARGE CORPORAUS 6,092,034 · 2000 METHOD AND APPARATUS FOR OPTIMIZING CONSTRAINT MODELSUS 6,031,984 · 2000 METHOD AND APPARATUS FOR COMPILING CONTEXT-DEPENDENT REWRITE RULES AND INPUT STRINGSUS 6,032,111 · 2000 STATISTICAL TRANSLATION SYSTEM WITH FEATURES BASED ON PHRASES OR GROUPS OF WORDSUS 5,991,710 · 1999

and 28 more

Cited by (39)

METHOD AND SYSTEM FOR PRESERVING PRIVACY IN AN HTTP COMMUNICATION BETWEEN A CLIENT AND A SERVERUS 11,763,032 · 2023 SYSTEMS AND METHODS FOR MONITORING POST TRANSLATION EDITINGUS 11,003,838 · 2021 Systems and Methods for Translating Textual ContentUS 10,984,429 · 2021 KERNEL-BASED VERBAL PHRASE SPLITTING DEVICES AND METHODSUS 10,741,171 · 2020 HIERARCHICAL DATA PROCESSOR TESTER

Related research

Chasing the Perfect Splitter: A Comparison of Different Compound Splitting ToolsSemantic Scholar Synthesizing Compound Words for Machine TranslationSemantic Scholar German Compounds and Statistical Machine Translation. Can they get along?Semantic Scholar Towards Unsupervised and Language-independent Compound Splitting using Inflectional Morphological TransformationsSemantic Scholar Massively Translingual Compound Analysis and Translation DiscoverySemantic Scholar

Full text

Google Patents