CN100535890C - 以arpa标准格式表示经删除插值n字母语言模型 - Google Patents
以arpa标准格式表示经删除插值n字母语言模型 Download PDFInfo
- Publication number
- CN100535890C CN100535890C CNB2005100601536A CN200510060153A CN100535890C CN 100535890 C CN100535890 C CN 100535890C CN B2005100601536 A CNB2005100601536 A CN B2005100601536A CN 200510060153 A CN200510060153 A CN 200510060153A CN 100535890 C CN100535890 C CN 100535890C
- Authority
- CN
- China
- Prior art keywords
- interpolation
- order
- probability
- letter
- word sequence
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/197—Probabilistic grammars, e.g. word n-grams
Abstract
Description
Claims (6)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/810,254 | 2004-03-26 | ||
US10/810,254 US7406416B2 (en) | 2004-03-26 | 2004-03-26 | Representation of a deleted interpolation N-gram language model in ARPA standard format |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1673997A CN1673997A (zh) | 2005-09-28 |
CN100535890C true CN100535890C (zh) | 2009-09-02 |
Family
ID=34862105
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2005100601536A Expired - Fee Related CN100535890C (zh) | 2004-03-26 | 2005-03-25 | 以arpa标准格式表示经删除插值n字母语言模型 |
Country Status (7)
Country | Link |
---|---|
US (1) | US7406416B2 (zh) |
EP (1) | EP1580667B1 (zh) |
JP (1) | JP4974470B2 (zh) |
KR (1) | KR101120773B1 (zh) |
CN (1) | CN100535890C (zh) |
AT (1) | ATE496342T1 (zh) |
DE (1) | DE602005025955D1 (zh) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8700404B1 (en) * | 2005-08-27 | 2014-04-15 | At&T Intellectual Property Ii, L.P. | System and method for using semantic and syntactic graphs for utterance classification |
US20070078653A1 (en) * | 2005-10-03 | 2007-04-05 | Nokia Corporation | Language model compression |
US20080282154A1 (en) * | 2006-09-11 | 2008-11-13 | Nurmi Mikko A | Method and apparatus for improved text input |
US7774197B1 (en) | 2006-09-27 | 2010-08-10 | Raytheon Bbn Technologies Corp. | Modular approach to building large language models |
US8332207B2 (en) * | 2007-03-26 | 2012-12-11 | Google Inc. | Large language models in machine translation |
KR101537078B1 (ko) * | 2008-11-05 | 2015-07-15 | 구글 인코포레이티드 | 사용자 정의 언어 모델들 |
US8798983B2 (en) * | 2009-03-30 | 2014-08-05 | Microsoft Corporation | Adaptation for statistical language model |
US8655647B2 (en) * | 2010-03-11 | 2014-02-18 | Microsoft Corporation | N-gram selection for practical-sized language models |
US9367526B1 (en) * | 2011-07-26 | 2016-06-14 | Nuance Communications, Inc. | Word classing for language modeling |
CN102982024B (zh) * | 2011-09-02 | 2016-03-23 | 北京百度网讯科技有限公司 | 一种搜索需求识别方法及装置 |
CN102509549B (zh) * | 2011-09-28 | 2013-08-14 | 盛乐信息技术(上海)有限公司 | 语言模型训练方法及系统 |
US9224386B1 (en) | 2012-06-22 | 2015-12-29 | Amazon Technologies, Inc. | Discriminative language model training using a confusion matrix |
US9292487B1 (en) * | 2012-08-16 | 2016-03-22 | Amazon Technologies, Inc. | Discriminative language model pruning |
US20150088511A1 (en) * | 2013-09-24 | 2015-03-26 | Verizon Patent And Licensing Inc. | Named-entity based speech recognition |
KR101509727B1 (ko) | 2013-10-02 | 2015-04-07 | 주식회사 시스트란인터내셔널 | 자율학습 정렬 기반의 정렬 코퍼스 생성 장치 및 그 방법과, 정렬 코퍼스를 사용한 파괴 표현 형태소 분석 장치 및 그 형태소 분석 방법 |
US9400783B2 (en) * | 2013-11-26 | 2016-07-26 | Xerox Corporation | Procedure for building a max-ARPA table in order to compute optimistic back-offs in a language model |
US10311046B2 (en) * | 2016-09-12 | 2019-06-04 | Conduent Business Services, Llc | System and method for pruning a set of symbol-based sequences by relaxing an independence assumption of the sequences |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US1940720A (en) * | 1931-03-16 | 1933-12-26 | Madsen Jens A Windfeld | Water softener |
US4096017A (en) * | 1977-02-18 | 1978-06-20 | H. C. Price Co. | Method and article for forming field joints on pipe coated with thermoplastic material |
US4111017A (en) * | 1977-06-21 | 1978-09-05 | The United States Of America As Represented By The United States Department Of Energy | Manually operated coded switch |
US5258909A (en) * | 1989-08-31 | 1993-11-02 | International Business Machines Corporation | Method and apparatus for "wrong word" spelling error detection and correction |
US5199464A (en) * | 1989-12-28 | 1993-04-06 | Interprovincial Pipe Line, Inc. | Pipeline repair sleeve assembly having heat sink groove |
US5267345A (en) * | 1992-02-10 | 1993-11-30 | International Business Machines Corporation | Speech recognition apparatus which predicts word classes from context and words from word classes |
IT1254723B (it) * | 1992-03-18 | 1995-10-09 | Snam Spa | Procedimento perfezionato per gli interventi di riparazione di danni localizzati alle condotte mediante applicazione di corazze con una guaina protettiva interposta |
EP0602296A1 (en) * | 1992-12-17 | 1994-06-22 | International Business Machines Corporation | Adaptive method for generating field dependant models for intelligent systems |
US5467425A (en) * | 1993-02-26 | 1995-11-14 | International Business Machines Corporation | Building scalable N-gram language models using maximum likelihood maximum entropy N-gram models |
JP2886121B2 (ja) * | 1995-11-10 | 1999-04-26 | 株式会社エイ・ティ・アール音声翻訳通信研究所 | 統計的言語モデル生成装置及び音声認識装置 |
US5937384A (en) | 1996-05-01 | 1999-08-10 | Microsoft Corporation | Method and system for speech recognition using continuous density hidden Markov models |
US5722463A (en) * | 1996-11-25 | 1998-03-03 | Petro-Line Upgrading Services Ltd. | External pipe reinforcing sleeve |
CA2192620C (en) * | 1996-12-11 | 2000-08-29 | Gerald Henderson | Pipe repair assembly |
US6188976B1 (en) | 1998-10-23 | 2001-02-13 | International Business Machines Corporation | Apparatus and method for building domain-specific language models |
JP2000250583A (ja) * | 1999-03-02 | 2000-09-14 | Atr Interpreting Telecommunications Res Lab | 統計的言語モデル生成装置及び音声認識装置 |
JP2000356997A (ja) | 1999-06-15 | 2000-12-26 | Atr Interpreting Telecommunications Res Lab | 統計的言語モデル生成装置及び音声認識装置 |
JP2001142881A (ja) | 1999-11-16 | 2001-05-25 | Nippon Telegr & Teleph Corp <Ntt> | 統計的言語モデル及びそれを用いた確率計算法 |
-
2004
- 2004-03-26 US US10/810,254 patent/US7406416B2/en not_active Expired - Fee Related
-
2005
- 2005-03-22 DE DE602005025955T patent/DE602005025955D1/de active Active
- 2005-03-22 AT AT05102283T patent/ATE496342T1/de not_active IP Right Cessation
- 2005-03-22 EP EP05102283A patent/EP1580667B1/en not_active Not-in-force
- 2005-03-25 CN CNB2005100601536A patent/CN100535890C/zh not_active Expired - Fee Related
- 2005-03-25 KR KR1020050024895A patent/KR101120773B1/ko active IP Right Grant
- 2005-03-28 JP JP2005092423A patent/JP4974470B2/ja active Active
Also Published As
Publication number | Publication date |
---|---|
EP1580667B1 (en) | 2011-01-19 |
JP2005293580A (ja) | 2005-10-20 |
US7406416B2 (en) | 2008-07-29 |
CN1673997A (zh) | 2005-09-28 |
KR20060044753A (ko) | 2006-05-16 |
EP1580667A3 (en) | 2007-10-10 |
DE602005025955D1 (de) | 2011-03-03 |
EP1580667A2 (en) | 2005-09-28 |
US20050216265A1 (en) | 2005-09-29 |
KR101120773B1 (ko) | 2012-03-23 |
JP4974470B2 (ja) | 2012-07-11 |
ATE496342T1 (de) | 2011-02-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100535890C (zh) | 以arpa标准格式表示经删除插值n字母语言模型 | |
CN1667699B (zh) | 为字母-声音转换生成有互信息标准的大文法音素单元 | |
CN109697282B (zh) | 一种语句的用户意图识别方法和装置 | |
CN1542736B (zh) | 用于将自然语言输入映射到大纲的系统和方法 | |
US20180357225A1 (en) | Method for generating chatting data based on artificial intelligence, computer device and computer-readable storage medium | |
CN101305362B (zh) | 语音索引删减 | |
CN100589179C (zh) | 从文本中预测误词率的方法和设备 | |
CN101283349B (zh) | 用Golomb码压缩语言模型 | |
US7860314B2 (en) | Adaptation of exponential models | |
CN111523306A (zh) | 文本的纠错方法、装置和系统 | |
US20060277033A1 (en) | Discriminative training for language modeling | |
CN111488462B (zh) | 基于知识图谱的推荐方法、装置、设备及介质 | |
US20080104056A1 (en) | Distributional similarity-based models for query correction | |
US20060020448A1 (en) | Method and apparatus for capitalizing text using maximum entropy | |
CN104854654A (zh) | 用于使用搜索查询信息的言语识别处理的方法和系统 | |
CN115062208B (zh) | 数据处理方法、系统及计算机设备 | |
CN102682017B (zh) | 一种信息检索方法和系统 | |
CN115455228A (zh) | 一种多模态数据互检方法、装置、设备及可读存储介质 | |
CN111460109A (zh) | 摘要及对话摘要生成方法和装置 | |
CN111143515B (zh) | 文本匹配方法及装置 | |
CN109902273B (zh) | 关键词生成模型的建模方法和装置 | |
CN113836308B (zh) | 网络大数据长文本多标签分类方法、系统、设备及介质 | |
CN110570877A (zh) | 手语视频生成方法、电子设备及计算机可读存储介质 | |
JP6261669B2 (ja) | クエリ校正システムおよび方法 | |
CN112735392B (zh) | 语音处理方法、装置、设备及存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
ASS | Succession or assignment of patent right |
Owner name: MICROSOFT TECHNOLOGY LICENSING LLC Free format text: FORMER OWNER: MICROSOFT CORP. Effective date: 20150508 |
|
C41 | Transfer of patent application or patent right or utility model | ||
TR01 | Transfer of patent right |
Effective date of registration: 20150508 Address after: Washington State Patentee after: Micro soft technique license Co., Ltd Address before: Washington State Patentee before: Microsoft Corp. |
|
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090902 Termination date: 20210325 |