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. 发明申请

US20220237380A1 INFERENCER, INFERENCE METHOD AND INFERENCE PROGRAM 有权
公开(公告)号：US20220237380A1
公开(公告)日：2022-07-28
申请号：US17617770
申请日：2020-07-06
申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY
发明人： Kehai CHEN , Rui WANG , Masao UCHIYAMA , Eiichiro SUMITA
IPC分类号： G06F40/284 , G06F40/126 , G06F40/166 , G06N5/04 , G06N3/08
摘要： Improvement is made in performance of a trained neural network that uses positional information indicating a position at which each token included in an input sequence is present in the input sequence. An inferencer includes a first generation unit that generates an intermediate sentence representation based on a first sentence representation having information indicating a value of each token included in the input sequence and first positional information indicating a position at which each token is present in the input sequence; a second generation unit that generates second positional information by modifying the first positional information based on the first sentence representation and the intermediate sentence representation, and that generates a hidden state representation based on the second positional information and the intermediate sentence representation; and a third generation unit that generates a second sentence representation based on the intermediate sentence representation and the hidden state representation.

2. 发明申请

US20160179790A1 TRANSLATION APPARATUS, LEARNING APPARATUS, TRANSLATION METHOD, AND STORAGE MEDIUM 审中-公开
标题翻译：翻译设备，学习设备，翻译方法和存储介质
公开(公告)号：US20160179790A1
公开(公告)日：2016-06-23
申请号：US14893197
申请日：2014-05-23
申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY
发明人： Taro WATANABE , Lemao LIU , Eiichiro SUMITA
IPC分类号： G06F17/28 , G06F17/30
CPC分类号： G06F17/289 , G06F16/313 , G06F17/2818 , G06F17/2836 , G06F17/2854
摘要： In order to solve a problem that, in the case of using a neural network that non-linearly links features, scores of translation candidates have to be calculated again during search, which requires an inordinate amount of effort, a translation apparatus includes: a parameter storage unit in which a first weight vector that is applied to a non-local feature function and a second weight vector that is applied to a local feature function can be stored; a feature function information storage unit in which non-local first feature function information and local second feature function information can be stored; a portion pair information storage unit in which two or more pieces of portion pair information such as a phrase pair or a rule pair can be stored; a score acquiring unit that acquires scores of two or more target language sentences by introducing a non-linear model to units of a phrase pair, a rule pair, or the like, and limiting the non-linear model to features closed to a phrase pair or a rule pair; a target language sentence acquiring unit that acquires a target language sentence with the largest score; and an output unit that outputs the target language sentence. Accordingly, in machine translation, translation can be precisely performed at high speed.
摘要翻译：为了解决在使用非线性链接特征的神经网络的情况下，必须在搜索期间再次计算翻译候选的分数，这需要过多的努力，翻译装置包括：参数可以存储应用于非局部特征函数的第一权重向量和应用于局部特征函数的第二加权向量的存储单元; 特征功能信息存储单元，其中可以存储非本地第一特征功能信息和本地第二特征功能信息; 部分对信息存储单元，其中可以存储诸如短语对或规则对的两个或更多个部分对信息; 分数获取单元，通过将非线性模型引入到短语对，规则对等单元中来获取两个或更多个目标语言句子的分数，并且将非线性模型限制到关闭到短语对的特征或规则对; 目标语言句子获取单元，其获取具有最大得分的目标语言句子; 以及输出目标语言句子的输出单元。因此，在机器平移中，可以高速精确地进行平移。

3. 发明申请

US20170154258A1 JOINT ESTIMATION METHOD AND METHOD OF TRAINING SEQUENCE-TO-SEQUENCE MODEL THEREFOR 审中-公开
公开(公告)号：US20170154258A1
公开(公告)日：2017-06-01
申请号：US14954190
申请日：2015-11-30
申请人： National Institute of Information and Communications Technology
发明人： Lemao LIU , Andrew FINCH , Masao UCHIYAMA , Eiichiro SUMITA
IPC分类号： G06N3/08
CPC分类号： G06N3/0454 , G06N3/0445
摘要： An estimation method utilizing a pair of target-directional models 106 and 108 includes the steps 160 and 164 of decoding an input 142 utilizing the first and the second models 106 and 108, thereby producing k-best hypotheses 162 and 166 from each of the first and the second models 106 and 108; calculating a union of the k-best hypotheses, and re-scoring 168 each of the best hypotheses in the union utilizing the first and the second models; and selecting a hypothesis 144 with the highest score.

4. 发明申请

US20170068665A1 WORD ALIGNMENT SCORE COMPUTING APPARATUS, WORD ALIGNMENT APPARATUS, AND COMPUTER PROGRAM 审中-公开
标题翻译：字对齐计算机，字对齐设备和计算机程序
公开(公告)号：US20170068665A1
公开(公告)日：2017-03-09
申请号：US15118703
申请日：2015-02-12
申请人： National Institute of Information and Communications Technology
发明人： Akihiro TAMURA , Taro WATANABE , Eiichiro SUMITA
IPC分类号： G06F17/28 , G10L25/30
CPC分类号： G06F17/2827 , G06F17/2818 , G10L25/30
摘要： [Object] An object is to provide an apparatus for attaining highly precise word alignment.[Solution] The apparatus includes: selecting means receiving a bilingual sentence pair and a word alignment for the bilingual sentence pair, for successively selecting words fj of a sentence in a first language in a prescribed order; and a recurrent neural network (RNN) 100, computing, for all words of the sentence in the first language, a score 102 representing a probability that a word pair consisting of the word fj and a word ea_{j} aligned with the word fj by a word alignment aj in a second language of the bilingual sentence pair is a correct word pair, and based on this score, for computing a score of the word alignment aj. When computing a score of word pair (fj, ea_{j}), RNN 100 computes a score 102 of the word pair (fj, ea_{j}) based on all word alignments a1j-1 selected by the selecting means prior to the word fj of the word pair (fj, ea_{j}), of the word alignments aj, by means of a recurrent connection 118.
摘要翻译： [解决方案]该装置包括：接收双语句对的双语语句对和单词对齐的选择单元，用于以规定的顺序依次选择第一语言的句子的单词fj; 和循环神经网络（RNN）100，对于第一语言中的句子的所有单词，计算表示由单词fj组成的单词对和与单词fj对齐的单词ea_ {j}的概率的分数102 通过双语句子对的第二语言中的单词对齐aj是正确的单词对，并且基于该分数，用于计算单词对齐aj的分数。当计算字对（fj，ea_ {j}）的分数时，RNN 100基于在选择装置选择的所有字对齐a1j-1之前计算字对（fj，ea_ {j}）的得分102 通过循环连接118，字对齐aj的字对（fj，ea_ {j}）的字fj。

5. 发明申请

US20210027026A1 PSEUDO PARALLEL TRANSLATION DATA GENERATION APPARATUS, MACHINE TRANSLATION PROCESSING APPARATUS, AND PSEUDO PARALLEL TRANSLATION DATA GENERATION METHOD 有权
公开(公告)号：US20210027026A1
公开(公告)日：2021-01-28
申请号：US16969619
申请日：2019-02-12
申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY
发明人： Kenji IMAMURA , Atsushi FUJITA , Eiichiro SUMITA
IPC分类号： G06F40/58 , G06N3/08 , G06K9/62
摘要： Provided are a model training method for neural machine translation that enhances an encoder using a monolingual corpus of a target language and improves the accuracy of the entire translator, and a machine translation system for performing the model training method. The machine translation system 1000 uses a monolingual corpus of the target language to obtain multiple pieces of pseudo source language data, thus allowing for obtaining a large amount of pseudo parallel corpus data having diversity. Further, the machine translation system 1000 uses both the pseudo parallel corpus data having diversity, which has been obtained in large quantities, and the base parallel corpus data in a small quantity but with high accuracy, with the applied learning rates changed accordingly, to perform the learning process (training process) for the machine translation model. This allows the machine translation system 1000 to obtain a learned model (machine translation model) with very high accuracy.

6. 发明申请

US20160132491A1 BILINGUAL PHRASE LEARNING APPARATUS, STATISTICAL MACHINE TRANSLATION APPARATUS, BILINGUAL PHRASE LEARNING METHOD, AND STORAGE MEDIUM 审中-公开
标题翻译：双极学习设备，统计机器翻译设备，双相学习方法和存储介质
公开(公告)号：US20160132491A1
公开(公告)日：2016-05-12
申请号：US14898431
申请日：2014-05-23
申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY
发明人： Taro WATANABE , Conghui ZHU , Eiichiro SUMITA
IPC分类号： G06F17/28 , G06F17/27
CPC分类号： G06F17/2818 , G06F17/2827
摘要： In order to solve a conventional problem that a translation model has to be updated each time a translation corpus is added, in a case of calculating a score of each phrase pair acquired from a j-th translation corpus (2≦j≦N) (added translation corpus), a score of each phrase pair corresponding to the j-th translation corpus is calculated using the one or more pieces of phrase appearance frequency information corresponding to a (j−1)-th translation corpus, the calculated score is used to generate a translation model, and the newly generated translation model is used in a state of being integrated to an original translation model. Accordingly, a translation model can be easily enhanced in a stepwise manner.
摘要翻译：为了解决每当添加翻译语料库时必须更新翻译模型的常规问题，在计算从第j翻译语料库（2＆amp; nlE; j＆nlE; N）获取的每个短语对的得分的情况下使用与第（j-1）个翻译语料库相对应的一个或多个短语出现频率信息来计算与第j个翻译语料库对应的每个短语组的分数，使用计算得分以生成翻译模型，并且将新生成的翻译模型用于与原始翻译模型集成的状态。因此，可以以逐步的方式容易地增强翻译模型。

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