Abstract: 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.

Abstract: 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.

Abstract: In order to solve a problem that the level of precision in inferring a crosslingual topic of documents or words in a non-parallel corpus associated in the document level is not high, a topic inferring apparatus includes: a word distribution information storage unit in which word distribution information is stored in association with each of two or more languages; a document topic distribution generating unit that acquires document topic distribution information of a multilingual document set; a segment topic distribution generating unit that acquires segment topic distribution information of each segment, using the document topic distribution information; and a word topic determining unit that determines, for each word contained in two or more documents contained in the multilingual document set, a topic of each word using the segment topic distribution information. Accordingly, it is possible to improve the level of precision in inferring a topic.

Abstract: In order to solve a problem that the level of precision in inferring a crosslingual topic of documents or words in a non-parallel corpus associated in the document level is not high, a topic inferring apparatus includes: a word distribution information storage unit in which word distribution information is stored in association with each of two or more languages; a document topic distribution generating unit that acquires document topic distribution information of a multilingual document set; a segment topic distribution generating unit that acquires segment topic distribution information of each segment, using the document topic distribution information; and a word topic determining unit that determines, for each word contained in two or more documents contained in the multilingual document set, a topic of each word using the segment topic distribution information. Accordingly, it is possible to improve the level of precision in inferring a topic.

Abstract: 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.

Abstract: [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.

Abstract: 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.

Abstract: [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.

Abstract: A conventional speech recognition dictionary, translation dictionary and speech synthesis dictionary used in speech translation have inconsistencies.

Abstract: 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 targ

Abstract: 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.

Abstract: Appropriate processing results or appropriate apparatuses can be selected with a control device that selects the most probable speech recognition result by using speech recognition scores received with speech recognition results from two or more speech recognition apparatuses; sends the selected speech recognition result to two or more translation apparatuses respectively; selects the most probable translation result by using translation scores received with translation results from the two or more translation apparatuses; sends the selected translation result to two or more speech synthesis apparatuses respectively; receives a speech synthesis processing result including a speech synthesis result and a speech synthesis score from each of the two or more speech synthesis apparatuses; selects the most probable speech synthesis result by using the scores; and sends the selected speech synthesis result to a second terminal apparatus.

Abstract: In conventional network-type speech translation systems, devices or models for recognizing or synthesizing speech cannot be changed in accordance with speakers' attributes, and therefore, accuracy is reduced or inappropriate output occurs in each process of speech recognition, translation, and speech synthesis. Accuracy of each processing of speech translation, translation, or speech synthesis is improved and appropriate output is performed in a network-type speech translation system by, based on speaker attributes, appropriately changing the server to perform speech recognition or the speech recognition model, appropriately changing the translation server to perform translation or the translation model, or appropriately changing the speech synthesis server or speech synthesis model.

Abstract: Appropriate processing results or appropriate apparatuses can be selected with a control device that selects the most probable speech recognition result by using speech recognition scores received with speech recognition results from two or more speech recognition apparatuses; sends the selected speech recognition result to two or more translation apparatuses respectively; selects the most probable translation result by using translation scores received with translation results from the two or more translation apparatuses; sends the selected translation result to two or more speech synthesis apparatuses respectively; receives a speech synthesis processing result including a speech synthesis result and a speech synthesis score from each of the two or more speech synthesis apparatuses; selects the most probable speech synthesis result by using the scores; and sends the selected speech synthesis result to a second terminal apparatus.

Abstract: In conventional network-type speech translation systems, devices or models for recognizing or synthesizing speech cannot be changed in accordance with speakers' attributes, and therefore, accuracy is reduced or inappropriate output occurs in each process of speech recognition, translation, and speech synthesis. Accuracy of each processing of speech translation, translation, or speech synthesis is improved and appropriate output is performed in a network-type speech translation system by, based on speaker attributes, appropriately changing the server to perform speech recognition or the speech recognition model, appropriately changing the translation server to perform translation or the translation model, or appropriately changing the speech synthesis server or speech synthesis model.

Abstract: A conventional speech recognition dictionary, translation dictionary and speech synthesis dictionary used in speech translation have inconsistencies.

Abstract: A method of machine translation, using a bilingual corpus containing translation pairs each consisting of a sentence of a first language and a sentence of a second language, for translating an input sentence of the first language to the second language, including the steps of: receiving the input sentence of the first language and extracting, from the bilingual corpus, a sentence of the second language forming a pair with a sentence of the first language with highest similarity to the input sentence; applying an arbitrary modification among a plurality of predetermined modifications to the extracted sentence of the second language, and computing likelihood of sentences resulting from the modification; selecting a prescribed number of sentences having high likelihood from among the sentences resulting from the modification; repeating, on each of the sentences selected in the step of selecting, the steps of extracting, computing and selecting, until the likelihood no longer improves; and outputting, as a transl

Abstract: A machine translation system includes: a distributing module for distributing an input sentence to a plurality of machine translation apparatuses for generating a translation of a second language of the input sentence of a first language, and receiving the translation of the second language from each of the plurality of translation apparatuses; a translation improving module, using each of the translations of the second language received by the distributing module as a starting point, improving the translation such that an evaluation in accordance with a prescribed evaluation method is improved; and a translation selecting module for selecting, as a translation of the input sentence, a translation satisfying a prescribed condition, among the translations improved by the translation improving module.

Abstract: A method of machine translation, using a bilingual corpus containing translation pairs each consisting of a sentence of a first language and a sentence of a second language, for translating an input sentence of the first language to the second language, including the steps of: receiving the input sentence of the first language and extracting, from the bilingual corpus, a sentence of the second language forming a pair with a sentence of the first language with highest similarity to the input sentence; applying an arbitrary modification among a plurality of predetermined modifications to the extracted sentence of the second language, and computing likelihood of sentences resulting from the modification; selecting a prescribed number of sentences having high likelihood from among the sentences resulting from the modification; repeating, on each of the sentences selected in the step of selecting, the steps of extracting, computing and selecting, until the likelihood no longer improves; and outputting, as a transl

Abstract: A method of improving translation knowledge includes the steps of preparing a set of translation knowledge, preparing a bilingual corpus of a source language and a target language, machine-translating sentences of the source language in the bilingual corpus to the target language using a set of translation knowledge, evaluating translation quality of the resulting translations in accordance with a prescribed evaluation standard, calculating degree of contribution to translation quality of a part of the translation knowledge, and removing the corresponding part of the translation knowledge when the calculated degree of contribution of the part is negative.