AU2001253060A1 - Cluster and pruning-based language model compression - Google Patents
Cluster and pruning-based language model compressionInfo
- Publication number
- AU2001253060A1 AU2001253060A1 AU2001253060A AU5306001A AU2001253060A1 AU 2001253060 A1 AU2001253060 A1 AU 2001253060A1 AU 2001253060 A AU2001253060 A AU 2001253060A AU 5306001 A AU5306001 A AU 5306001A AU 2001253060 A1 AU2001253060 A1 AU 2001253060A1
- Authority
- AU
- Australia
- Prior art keywords
- pruning
- cluster
- language model
- based language
- model compression
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/565,608 | 2000-05-04 | ||
US09/565,608 US6782357B1 (en) | 2000-05-04 | 2000-05-04 | Cluster and pruning-based language model compression |
PCT/US2001/010536 WO2001084357A2 (en) | 2000-05-04 | 2001-03-31 | Cluster and pruning-based language model compression |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2001253060A1 true AU2001253060A1 (en) | 2001-11-12 |
Family
ID=24259379
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2001253060A Abandoned AU2001253060A1 (en) | 2000-05-04 | 2001-03-31 | Cluster and pruning-based language model compression |
Country Status (3)
Country | Link |
---|---|
US (1) | US6782357B1 (en) |
AU (1) | AU2001253060A1 (en) |
WO (1) | WO2001084357A2 (en) |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4105841B2 (en) * | 2000-07-11 | 2008-06-25 | インターナショナル・ビジネス・マシーンズ・コーポレーション | Speech recognition method, speech recognition apparatus, computer system, and storage medium |
TW472232B (en) * | 2000-08-11 | 2002-01-11 | Ind Tech Res Inst | Probability-base fault-tolerance natural language understanding method |
US7162694B2 (en) * | 2001-02-13 | 2007-01-09 | Microsoft Corporation | Method for entering text |
US7385591B2 (en) * | 2001-03-31 | 2008-06-10 | Microsoft Corporation | Out-of-vocabulary word determination and user interface for text input via reduced keypad keys |
US7117144B2 (en) * | 2001-03-31 | 2006-10-03 | Microsoft Corporation | Spell checking for text input via reduced keypad keys |
US7103534B2 (en) * | 2001-03-31 | 2006-09-05 | Microsoft Corporation | Machine learning contextual approach to word determination for text input via reduced keypad keys |
CN100530171C (en) * | 2005-01-31 | 2009-08-19 | 日电(中国)有限公司 | Dictionary learning method and devcie |
KR100703697B1 (en) * | 2005-02-02 | 2007-04-05 | 삼성전자주식회사 | Method and Apparatus for recognizing lexicon using lexicon group tree |
US8165870B2 (en) * | 2005-02-10 | 2012-04-24 | Microsoft Corporation | Classification filter for processing data for creating a language model |
US7351973B2 (en) * | 2005-02-15 | 2008-04-01 | Delphi Technologies, Inc. | Apparatus and method for providing thermal conductance in thermally responsive photonic imaging devices |
WO2006088801A1 (en) * | 2005-02-15 | 2006-08-24 | Delphi Technologies, Inc. | Filter assembly and method of filtering electromagnetic radiation |
US20060180759A1 (en) * | 2005-02-15 | 2006-08-17 | Mantese Joseph V | System and method for controlling pyroelectric sensors in a focal plane array |
US9471566B1 (en) * | 2005-04-14 | 2016-10-18 | Oracle America, Inc. | Method and apparatus for converting phonetic language input to written language output |
US20070078653A1 (en) * | 2005-10-03 | 2007-04-05 | Nokia Corporation | Language model compression |
US8249871B2 (en) * | 2005-11-18 | 2012-08-21 | Microsoft Corporation | Word clustering for input data |
US8176016B1 (en) * | 2006-11-17 | 2012-05-08 | At&T Intellectual Property Ii, L.P. | Method and apparatus for rapid identification of column heterogeneity |
CN101271450B (en) * | 2007-03-19 | 2010-09-29 | 株式会社东芝 | Method and device for cutting language model |
US9069755B2 (en) * | 2010-03-11 | 2015-06-30 | Microsoft Technology Licensing, Llc | N-gram model smoothing with independently controllable parameters |
US9529898B2 (en) | 2014-08-26 | 2016-12-27 | Google Inc. | Clustering classes in language modeling |
US9953646B2 (en) | 2014-09-02 | 2018-04-24 | Belleau Technologies | Method and system for dynamic speech recognition and tracking of prewritten script |
US10134389B2 (en) | 2015-09-04 | 2018-11-20 | Microsoft Technology Licensing, Llc | Clustering user utterance intents with semantic parsing |
JP6988817B2 (en) * | 2016-11-14 | 2022-01-05 | 日本電気株式会社 | Predictive model generation system, method and program |
US11620435B2 (en) | 2019-10-10 | 2023-04-04 | International Business Machines Corporation | Domain specific model compression |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5835893A (en) * | 1996-02-15 | 1998-11-10 | Atr Interpreting Telecommunications Research Labs | Class-based word clustering for speech recognition using a three-level balanced hierarchical similarity |
US6314339B1 (en) * | 1997-10-01 | 2001-11-06 | The Research Foundation Of State University Of New York | Method and apparatus for optimizing an actual motion to perform a desired task by a performer |
US6317707B1 (en) * | 1998-12-07 | 2001-11-13 | At&T Corp. | Automatic clustering of tokens from a corpus for grammar acquisition |
US6415248B1 (en) * | 1998-12-09 | 2002-07-02 | At&T Corp. | Method for building linguistic models from a corpus |
-
2000
- 2000-05-04 US US09/565,608 patent/US6782357B1/en not_active Expired - Lifetime
-
2001
- 2001-03-31 AU AU2001253060A patent/AU2001253060A1/en not_active Abandoned
- 2001-03-31 WO PCT/US2001/010536 patent/WO2001084357A2/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
WO2001084357A3 (en) | 2002-08-15 |
WO2001084357A2 (en) | 2001-11-08 |
US6782357B1 (en) | 2004-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2001253060A1 (en) | Cluster and pruning-based language model compression | |
AU2001245348A1 (en) | Language model sharing | |
AU2001263417A1 (en) | Unified language model cfg and n-grams | |
AU2002235128A1 (en) | Expression miniarrays and uses thereof | |
AU2002237495A1 (en) | Dynamic natural language understanding | |
AU2002226072A1 (en) | Value-instance-connectivity-computer-implemented database | |
AU2001245811A1 (en) | Database system and method | |
AU2002223296A1 (en) | Modeling object interactions and facial expressions | |
AU2001283067A1 (en) | Transcript management software and methods therefor | |
AU2001213236A1 (en) | Mini-cyclone biocollector and concentrator | |
AU2001287898A1 (en) | Pyrazolopyridines and pyrazolopyridazines as antidiabetics | |
AU2003271224A1 (en) | Fibrous nano-carbon and preparation method thereof | |
AU2001282424A1 (en) | Wireless interactive system and method | |
AU2001253418A1 (en) | Compounds and methods | |
AU2001270247A1 (en) | Low profile speaker and system | |
AU2002357156A1 (en) | Geographically-based databases and methods | |
AU2001243394A1 (en) | Compounds and methods | |
AU2001292936A1 (en) | Octahydro-indolizines and quinolizines and hexahydro-pyrrolizines | |
AU2001269405A1 (en) | Dynamic range compression method | |
AU2001295185A1 (en) | Multiplexing-interleaving and demultiplexing-deinterleaving | |
AU2001268416A1 (en) | Basis functions of three-dimensional models for compression, transformation and streaming | |
AUPQ872300A0 (en) | Compounds and methods | |
AU2001264300A1 (en) | Dynode producing method and structure | |
AU2001241297A1 (en) | An alkoxylenation catalyst and a method to manufacture the alkoxylenation catalyst | |
AU2001278951A1 (en) | Compounds and methods |