专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08452585B2 Discriminative syntactic word order model for machine translation 有权
标题翻译：用于机器翻译的判别句法词序列模型
公开(公告)号：US08452585B2
公开(公告)日：2013-05-28
申请号：US12061313
申请日：2008-04-02
申请人： Kristina Nikolova Toutanova , Pi-Chuan Chang
发明人： Kristina Nikolova Toutanova , Pi-Chuan Chang
IPC分类号： G06F17/27
CPC分类号： G06F17/2818
摘要： A discriminatively trained word order model is used to identify a most likely word order from a set of word orders for target words translated from a source sentence. For each set of word orders, the discriminatively trained word order model uses features based on information in a source dependency tree and a target dependency tree and features based on the order of words in the word order. The discriminatively trained statistical model is trained by determining a translation metric for each of a set of N-best word orders for a set of target words. Each of the N-best word orders are projective with respect to a target dependency tree and the N-best word orders are selected using a combination of an n-gram language model and a local tree order model.
摘要翻译：使用歧视性训练的词序模型来识别从源语句翻译的目标词的一组单词顺序中最可能的单词顺序。对于每个单词组，鉴别训练的词序模型基于源依赖树中的信息和目标依赖关系树和基于单词中单词顺序的特征来使用特征。通过针对一组目标单词的一组N个最佳单词顺序中的每一个确定翻译度量来训练经歧视地训练的统计模型。每个N最好的单词顺序相对于目标依赖关系树是投影的，并且使用n-gram语言模型和本地树顺序模型的组合来选择N个最好的单词顺序。

2. 发明申请

US20080319736A1 Discriminative Syntactic Word Order Model for Machine Translation 有权
标题翻译：机器翻译判别语法词序模型
公开(公告)号：US20080319736A1
公开(公告)日：2008-12-25
申请号：US12061313
申请日：2008-04-02
申请人： Kristina Nikolova Toutanova , Pi-Chuan Chang
发明人： Kristina Nikolova Toutanova , Pi-Chuan Chang
IPC分类号： G06F17/27
CPC分类号： G06F17/2818
摘要： A discriminatively trained word order model is used to identify a most likely word order from a set of word orders for target words translated from a source sentence. For each set of word orders, the discriminatively trained word order model uses features based on information in a source dependency tree and a target dependency tree and features based on the order of words in the word order. The discriminatively trained statistical model is trained by determining a translation metric for each of a set of N-best word orders for a set of target words. Each of the N-best word orders are projective with respect to a target dependency tree and the N-best word orders are selected using a combination of an n-gram language model and a local tree order model.
摘要翻译：使用歧视性训练的词序模型来识别从源语句翻译的目标词的一组单词顺序中最可能的单词顺序。对于每个单词组，鉴别训练的词序模型基于源依赖树中的信息和目标依赖关系树和基于单词中单词顺序的特征来使用特征。通过针对一组目标单词的一组N个最佳单词顺序中的每一个确定翻译度量来训练经歧视地训练的统计模型。每个N最好的单词顺序相对于目标依赖关系树是投影的，并且使用n-gram语言模型和本地树顺序模型的组合来选择N个最好的单词顺序。

3. 发明授权

US08275607B2 Semi-supervised part-of-speech tagging 有权
标题翻译：半监督的词性标签
公开(公告)号：US08275607B2
公开(公告)日：2012-09-25
申请号：US11954212
申请日：2007-12-12
申请人： Kristina Nikolova Toutanova , Mark Edward Johnson
发明人： Kristina Nikolova Toutanova , Mark Edward Johnson
IPC分类号： G06F17/27
CPC分类号： G06F17/2755
摘要： A word is selected from a received text and features are identified from the word. The features are applied to a model to identify probabilities for sets of part-of-speech tags. The probabilities for the sets of part-of-speech tags are used to weight scores for possible part-of-speech tags for the selected word to form weighted scores. The weighted scores are used to select a part-of-speech tag for the word and the selected part of speech tag is stored or output. The scores for the possible part-of-speech tags are based on variational approximation parameters trained from a sparse prior over probability distributions describing the probability of a part-of-speech tag given a word.
摘要翻译：从接收到的文本中选择一个单词，并从单词中识别特征。这些特征被应用于模型以识别词性标签集合的概率。部分语音标签集合的概率用于对所选词的可能词性标签加权分数以形成加权分数。加权分数用于选择单词的词性标签，并存储或输出所选择的部分语音标签。可能的词性标签的分数基于从稀疏先验概率分布训练的变分近似参数，描述了给定词的词性标签的概率。

4. 发明申请

US20090326916A1 UNSUPERVISED CHINESE WORD SEGMENTATION FOR STATISTICAL MACHINE TRANSLATION 审中-公开
标题翻译：不平衡中文字数统计机翻译
公开(公告)号：US20090326916A1
公开(公告)日：2009-12-31
申请号：US12163119
申请日：2008-06-27
申请人： Jianfeng Gao , Kristina Nikolova Toutanova , Jia Xu
发明人： Jianfeng Gao , Kristina Nikolova Toutanova , Jia Xu
IPC分类号： G06F17/28
CPC分类号： G06F17/2827 , G06F17/277 , G06F17/2818 , G06F17/2863
摘要： Described is using a generative model in processing an unsegmented sentence into a segmented sentence. A segmenter includes the generative model, which given an unsegmented sentence (e.g., in Chinese) provides candidate segmented sentences to a probability-based decoder that selects the segmented sentence. For example, the segmented (e.g., Chinese-language) sentence may be provided to a statistical machine translator that outputs a translated (e.g., English-language) sentence. The generative model may include a word sub-model that generates hidden words using a word model, a spelling sub-model that generates characters from the hidden words, and an alignment sub-model that generates translated words and alignment data from the characters. The word sub-model may correspond to a unigram model having words and associated frequency data therein, and the alignment sub-model may correspond to a word aligned corpus having source sentence, translated target sentence pairings therein. Training is also described.
摘要翻译：描述的是使用生成模型将未分段句子处理为分段句子。分割器包括生成模型，其给出未分段句子（例如，中文），将候选分割句子提供给选择分割句子的基于概率的解码器。例如，可以将分段（例如，中文）语句提供给输出翻译（例如，英语）句子的统计机器翻译器。生成模型可以包括使用单词模型生成隐藏单词的单词子模型，从隐藏单词生成字符的拼写子模型以及从字符生成翻译单词和对齐数据的对齐子模型。单词子模型可以对应于其中具有单词和相关联的频率数据的单格式模型，并且对齐子模型可以对应于具有源语句的单词对齐语料库，其中翻译的目标句子对。培训也被描述。

5. 发明申请

US20090157384A1 SEMI-SUPERVISED PART-OF-SPEECH TAGGING 有权
标题翻译：半监督的部分话题标签
公开(公告)号：US20090157384A1
公开(公告)日：2009-06-18
申请号：US11954212
申请日：2007-12-12
申请人： Kristina Nikolova Toutanova , Mark Edward Johnson
发明人： Kristina Nikolova Toutanova , Mark Edward Johnson
IPC分类号： G06F17/28
CPC分类号： G06F17/2755
摘要： A word is selected from a received text and features are identified from the word. The features are applied to a model to identify probabilities for sets of part-of-speech tags. The probabilities for the sets of part-of-speech tags are used to weight scores for possible part-of-speech tags for the selected word to form weighted scores. The weighted scores are used to select a part-of-speech tag for the word and the selected part of speech tag is stored or output. The scores for the possible part-of-speech tags are based on variational approximation parameters trained from a sparse prior over probability distributions describing the probability of a part-of-speech tag given a word.
摘要翻译：从接收到的文本中选择一个单词，并从单词中识别特征。这些特征被应用于模型以识别词性标签集合的概率。部分语音标签集合的概率用于对所选词的可能词性标签加权分数以形成加权分数。加权分数用于选择单词的词性标签，并存储或输出所选择的部分语音标签。可能的词性标签的分数基于从稀疏的先验概率分布训练的变分近似参数，描述了给定词的词性标签的概率。

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