专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US06295529B1 Method and apparatus for indentifying clauses having predetermined characteristics indicative of usefulness in determining relationships between different texts 有权
标题翻译：用于识别具有指示在确定不同文本之间的关系中有用的预定特征的条款的方法和装置
公开(公告)号：US06295529B1
公开(公告)日：2001-09-25
申请号：US09220836
申请日：1998-12-24
申请人： Simon H. Corston-Oliver , William B. Dolan
发明人： Simon H. Corston-Oliver , William B. Dolan
IPC分类号： G06F1730
CPC分类号： G06F17/2211 , G06F17/30684 , Y10S707/917 , Y10S707/99933 , Y10S707/99939
摘要： A system is utilized for determining a relationship between first and second textual inputs. The system identifies clauses in the first textual input having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the clauses identified. The clauses can be eliminated from the first textual input, weighted in the first textual input, or simply annotated.
摘要翻译：系统用于确定第一和第二文本输入之间的关系。系统识别具有指示在确定关系中有用的预定特征的第一文本输入中的条款。然后根据所确定的条款确定关系。这些条款可以从第一个文本输入中消除，在第一个文本输入中加权，或者简单地注释。

22. 发明授权

US5933822A Apparatus and methods for an information retrieval system that employs natural language processing of search results to improve overall precision 失效
标题翻译：一种信息检索系统的装置和方法，其使用搜索结果的自然语言处理来提高总体精度
公开(公告)号：US5933822A
公开(公告)日：1999-08-03
申请号：US898652
申请日：1997-07-22
申请人： Lisa Braden-Harder , Simon H. Corston , William B. Dolan , Lucy H. Vanderwende
发明人： Lisa Braden-Harder , Simon H. Corston , William B. Dolan , Lucy H. Vanderwende
IPC分类号： G06F17/28 , G06F17/30 , G06F17/00
CPC分类号： G06F17/30684 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936
摘要： Apparatus and accompanying methods for an information retrieval system that utilizes natural language processing to process results retrieved by, for example, an information retrieval engine such as a conventional statistical-based search engine, in order to improve overall precision. Specifically, such a search ultimately yields a set of retrieved documents. Each such document is then subjected to natural language processing to produce a set of logical forms. Each such logical form encodes, in a word-relation-word manner, semantic relationships, particularly argument and adjunct structure, between words in a phrase. A user-supplied query is analyzed in the same manner to yield a set of corresponding logical forms therefor. Documents are ranked as a predefined function of the logical forms from the documents and the query. Specifically, the set of logical forms for the query is then compared against a set of logical forms for each of the retrieved documents in order to ascertain a match between any such logical forms in both sets. Each document that has at least one matching logical forms is heuristically scored, with each different relation for a matching logical forms being assigned a different corresponding predefined weight. The score of each such document is, e.g., a predefined function of the weights of its uniquely matching logical forms. Finally, the retained documents are ranked in order of descending score and then presented to a user in that order.
摘要翻译：用于信息检索系统的设备和附带方法，其利用自然语言处理来处理例如诸如常规的基于统计的搜索引擎之类的信息检索引擎检索的结果，以便提高总体精度。具体来说，这样的搜索最终产生一组检索的文档。然后，每个这样的文档都进行自然语言处理，以产生一组逻辑形式。每个这样的逻辑形式以单词关系字的方式编码短语中的单词之间的语义关系，特别是参数和辅助结构。以相同的方式分析用户提供的查询，以产生一组相应的逻辑形式。文档被排序为来自文档和查询的逻辑表单的预定义函数。具体来说，然后将查询的逻辑形式集合与针对每个检索到的文档的一组逻辑形式进行比较，以便确定两个集合中任何这样的逻辑形式之间的匹配。具有至少一个匹配逻辑形式的每个文档被启发式地评分，对于匹配的逻辑形式的每个不同关系被分配不同的对应的预定权重。每个这样的文档的得分是例如其唯一匹配的逻辑形式的权重的预定函数。最后，保留的文档按照降序的顺序排列，然后以该顺序呈现给用户。

23. 发明申请

US20120109623A1 Stimulus Description Collections 审中-公开
标题翻译：刺激描述收藏
公开(公告)号：US20120109623A1
公开(公告)日：2012-05-03
申请号：US12916951
申请日：2010-11-01
申请人： William B. Dolan , David L. Chen
发明人： William B. Dolan , David L. Chen
IPC分类号： G06F17/28
CPC分类号： G06F17/2827
摘要： The subject disclosure generally describes a technology by which text and/or speech descriptions are collected by showing a stimulus such as video clips to contributors (e.g., of a crowd-sourcing service). The descriptions, which are in the language of each contributor's choice, are of the same stimulus and thus associated with one another. While each contributor may be monolingual, the technique allows for the collection of approximately bilingual data, since more than one language may be represented among the different contributors. The descriptions may be used as translation data for training a machine translation engine, and as paraphrase data (grouped by the same language) for training a machine paraphrasing system. Also described is evaluating the quality of a machine paraphrasing system via a distinctiveness metric.
摘要翻译：主题公开一般地描述了通过向贡献者（例如，群众来源服务）显示诸如视频剪辑的刺激来收集文本和/或语音描述的技术。每个贡献者选择的语言的描述是相同的刺激，因此彼此相关联。虽然每个贡献者可以是单语的，但是该技术允许收集大致双语数据，因为可以在不同的贡献者中表示多于一种的语言。这些描述可以用作训练机器翻译引擎的翻译数据，以及用于训练机器翻译系统的转义数据（以相同的语言分组）。还描述了通过独特性度量来评估机器释义系统的质量。

24. 发明授权

US07299238B2 System for improving the performance of information retrieval-type tasks by identifying the relations of constituents 有权
标题翻译：通过确定组成部分的关系，提高信息检索类型任务的绩效的系统
公开(公告)号：US07299238B2
公开(公告)日：2007-11-20
申请号：US10979532
申请日：2004-11-02
申请人： Simon H. Corston-Oliver , William B. Dolan , Hisami Suzuki
发明人： Simon H. Corston-Oliver , William B. Dolan , Hisami Suzuki
IPC分类号： G06F17/30
CPC分类号： G06F17/30684 , B42D15/00 , B42D15/0053 , Y10S707/917 , Y10S707/954 , Y10S707/956 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99942 , Y10S707/99943 , Y10S707/99944 , Y10S707/99945
摘要： A system is utilized for determining a relationship between first and second textual inputs. The system identifies constituents in the first textual input, having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the constituents identified. The constituents can be eliminated from the first textual input, weighted in the first textual input, or simply annotated in one of a variety of ways.
摘要翻译：系统用于确定第一和第二文本输入之间的关系。系统识别第一文本输入中的成分，具有指示在确定关系中有用的预定特征。然后根据所确定的成分确定关系。组成成分可以从第一个文本输入中消除，在第一个文本输入中加权，或者以各种方式简单地注释。

25. 发明授权

US06901399B1 System for processing textual inputs using natural language processing techniques 失效
标题翻译：使用自然语言处理技术处理文本输入的系统
公开(公告)号：US06901399B1
公开(公告)日：2005-05-31
申请号：US09097979
申请日：1998-06-16
申请人： Simon H. Corston , William B. Dolan , Lucy H. Vanderwende , Lisa Braden-Harder
发明人： Simon H. Corston , William B. Dolan , Lucy H. Vanderwende , Lisa Braden-Harder
IPC分类号： G06F17/28 , G06F17/30
CPC分类号： G06F17/30684 , Y10S707/99932 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936
摘要： A system filters documents in a document set retrieved from a document store in response to a query. The system obtains a first set of logical forms based on a selected one of the query and the documents in the document set. The system obtains a second set of logical forms based on another of the query and the documents in the document set. The system then uses natural language processing techniques to modify the first logical forms to obtain a modified set of logical forms. The system filters documents in the document set based on a predetermined relationship between the modified set of logical forms and the second set of logical forms.
摘要翻译：系统会根据查询过滤从文档存储检索的文档集中的文档。系统基于文档集中的查询和文档中的所选择的一个获得第一组逻辑形式。该系统基于文档集中的另一查询和文档获得第二组逻辑形式。然后，系统使用自然语言处理技术来修改第一逻辑形式以获得修改的逻辑形式集合。系统基于修改的逻辑形式集合和第二组逻辑形式之间的预定关系来过滤文档集中的文档。

26. 发明授权

US06521020B2 Claus feed gas hydrocarbon removal 有权
公开(公告)号：US06521020B2
公开(公告)日：2003-02-18
申请号：US10096908
申请日：2002-03-14
申请人： Kenneth F. Butwell , William B. Dolan , Steven M. Kuznicki
发明人： Kenneth F. Butwell , William B. Dolan , Steven M. Kuznicki
IPC分类号： B01D5304
CPC分类号： B01D53/8615 , B01D53/04 , B01D53/0462 , B01D53/047 , B01D2253/106 , B01D2253/108 , B01D2253/1085 , B01D2256/24 , B01D2259/40086 , B01D2259/402 , B01D2259/403 , Y10S95/902
摘要： A process for adsorbing hydrocarbons from an acid gas stream includes passing the acid gas stream through an adsorbent which selectively removes hydrocarbons, desorbing the hydrocarbons from the adsorbent and contacting the desorbed hydrocarbons with an acid gas removal solution to remove acid gases which have been coadsorbed with the hydrocarbons. The process is particularly useful in removing hydrocarbons from a hydrogen sulfide-containing stream which is being directed to Claus processing for conversion into elemental sulfur. Useful adsorbents include crystalline titanium silicate molecular sieves containing titania octahedral sites such as ETS-10 and similar materials, as well as high silica aluminosilicate zeolite.

27. 发明授权

US06349316B2 Document summarizer for word processors 有权
公开(公告)号：US06349316B2
公开(公告)日：2002-02-19
申请号：US09289085
申请日：1999-04-08
申请人： Ronald A. Fein , William B. Dolan , John Messerly , Edward J. Fries , Christopher A. Thorpe , Shawn J. Cokus
发明人： Ronald A. Fein , William B. Dolan , John Messerly , Edward J. Fries , Christopher A. Thorpe , Shawn J. Cokus
IPC分类号： G06F1500
CPC分类号： G06F17/277 , G06F17/2715 , G06F17/2755 , G06F17/2775 , G06F17/2785 , G06F17/279 , G06F17/30719
摘要： An author-oriented document summarizer for a word processor is described. The document summarizer performs a statistical analysis to generate a list of ranked sentences for consideration in the summary. The summarizer counts how frequently content words appear in a document and produces a table correlating the content words with their corresponding frequency counts. Phrase compression techniques are used to produce more accurate counts of repeatedly used phrases. A sentence score for each sentence is derived by summing the frequency counts of the content words in a sentence and dividing that tally by the number of the content words in the sentence. The sentences are then ranked in order of their sentence scores. Concurrent with the statistical analysis, during the same pass through the document the summarizer performs a cue-phrase analysis to weed out sentences with words or phrases that have been pre-identified as potential problem phrases. The cue-phrase analysis compares sentence phrases with a pre-compiled list of words and phrases and sets conditions on whether the sentences containing them can be used in the summary. Following the cue-phrase analysis, the summarizer creates a summary containing the higher ranked sentences. The summary may also include a conditioned sentence if the conditions established for inclusion of the sentence have been satisfied. The summarizer then inserts the sentence at the beginning of the document before the start of the text.

28. 发明授权

US06197092B1 Selective removal of nitrogen from natural gas by pressure swing adsorption 有权
公开(公告)号：US06197092B1
公开(公告)日：2001-03-06
申请号：US09273684
申请日：1999-03-22
申请人： Kenneth F. Butwell , William B. Dolan , Steven M. Kuznicki
发明人： Kenneth F. Butwell , William B. Dolan , Steven M. Kuznicki
IPC分类号： B01D53047
CPC分类号： B01D53/047 , B01D53/02 , B01D2253/102 , B01D2253/104 , B01D2253/106 , B01D2253/108 , B01D2253/308 , B01D2256/10 , B01D2256/24 , B01D2258/06 , B01D2259/40052 , Y02C20/20 , Y10S95/902
摘要： A pressure swing adsorption process for the separation of hydrogen from a mixture of the same with methane, utilizing two separate PSA stages, one containing a nitrogen selective crystalline zeolite, and the second containing a methane selective adsorbent.

29. 发明授权

US6081775A Bootstrapping sense characterizations of occurrences of polysemous words in dictionaries 有权
公开(公告)号：US6081775A
公开(公告)日：2000-06-27
申请号：US334391
申请日：1999-06-16
申请人： William B. Dolan
发明人： William B. Dolan
IPC分类号： G06F17/27 , G06F17/28 , G06F17/21 , G06F17/30
CPC分类号： G06F17/2795
摘要： The present invention is directed to characterizing the sense of an occurrence of a polysemous word in a representation of a dictionary. In a preferred embodiment, the representation of the dictionary is made up of a plurality of text segments containing word occurrences having a word sense characterization and word occurrences not having a word sense characterization. The embodiment first selects a plurality of the dictionary text segments that each contain a first word. The embodiment then identifies from among the selected text segments a first and a second occurrence of a second word. The identified second occurrence of the second word has a word sense characterization. The embodiment then attributes to the first occurrence of the second word sense characterization of the second occurrence of the second word.

30. 发明授权

US06078878A Bootstrapping sense characterizations of occurrences of polysemous words 失效
标题翻译：多义词发生的引导意义表征
公开(公告)号：US06078878A
公开(公告)日：2000-06-20
申请号：US904422
申请日：1997-07-31
申请人： William B. Dolan
发明人： William B. Dolan
IPC分类号： G06F17/27
CPC分类号： G06F17/2795
摘要： The present invention is directed to characterizing the sense of an occurrence of a polysemous word in a representation of a dictionary. In a preferred embodiment, the representation of the dictionary is made up of a plurality of text segments containing word occurrences having a word sense characterization and word occurrences not having a word sense characterization. The embodiment first selects a plurality of the dictionary text segments that each contain a first word. The embodiment then identifies from among the selected text segments a first and a second occurrence of a second word. The identified second occurrence of the second word has a word sense characterization. The embodiment then attributes to the first occurrence of the second word sense characterization of the second occurrence of the second word.
摘要翻译：本发明旨在表征词典表示中多义词的发生的感觉。在优选实施例中，词典的表示由多个文本段组成，该文本段包含具有单词检测特性的单词出现和不具有词义特征的单词出现。该实施例首先选择每个包含第一个字的多个字典文本段。然后，该实施例从选定的文本段中识别第二个字的第一和第二个出现。所识别的第二个字的第二次出现具有词义特性。然后，该实施例归因于第二个字的第二次出现的第二个字感应表征的第一次出现。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式