Abstract: A simultaneous translation system includes: an encoder encoding an input word sequence to an intermediate language representation; a chunk-end detecting device detecting an end of a chunk in the word sequence; a word vector reading unit inputting a partial word sequence up to the chunk-end detected by the chunk-end detecting device to the encoder; a decoder and a translated word searching unit receiving the intermediate language representation from encoder as an input, for outputting a translation word sequence corresponding to the partial word sequence; and a translated word sequence storage unit storing the translation word sequences output by decoder and translated word searching unit.

Abstract: A Latin character conversion apparatus includes a code associator that associates each of a plurality of character keys assigned with Latin characters among a plurality of keys included in a keyboard with any of a plurality of character codes established by a character encoding scheme of the Unicode Standard, a character associator that associates the character code with a relevant code being another character code, a code converter that, in response to an instruction by a user that instructs any of the plurality of character keys, determines the character code associated with the instructed character key as a conversion candidate, and a character converter that, in response to an instruction by the user that instructs the character key serving also as a conversion key of the plurality of character keys with the conversion candidate determined, converts the conversion candidate into the relevant code associated with the conversion candidate.

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: A Latin character conversion apparatus includes a code associator that associates each of a plurality of character keys assigned with Latin characters among a plurality of keys included in a keyboard with any of a plurality of character codes established by a character encoding scheme of the Unicode Standard, a character associator that associates the character code with a relevant code being another character code, a code converter that, in response to an instruction by a user that instructs any of the plurality of character keys, determines the character code associated with the instructed character key as a conversion candidate, and a character converter that, in response to an instruction by the user that instructs the character key serving also as a conversion key of the plurality of character keys with the conversion candidate determined, converts the conversion candidate into the relevant code associated with the conversion candidate.

Abstract: A syntax analyzing device includes: a syntax analyzing unit that analyzes syntax of a sentence received by a receiving unit, thereby acquiring a first analysis result, which is an analysis result having one or more elements constituting the sentence and parts of speech of the respective one or more elements and has one or more binary trees each having the parts of speech or the elements as nodes; a category acquiring unit that acquires categories of the respective one or more elements constituting the sentence; a category inserting unit that acquires a second analysis result in which the categories of the elements are respectively inserted between the elements and the parts of speech of the elements, which respectively correspond to the one or more categories, and constituting the first analysis result; and a learning unit that outputs the second analysis result acquired by the category inserting unit.

Abstract: A machine translation apparatus 230 capable of appropriately translating source sentences differently in accordance with information exceeding the scope of source sentences includes: a grammatical type determining unit 282 for identifying grammatical type of a source sentence; a grammatical-type-based tagging unit 286 for adding first and second tags corresponding to the grammatical type to head and tail positions of the source sentence, respectively; and a phrase-based statistical machine translation apparatus 288 configured to receive the source sentence having the first and second tags added. Different types are defined as grammatical types. The grammatical type determining unit 282 selects the first and second tags in accordance with the different grammatical types.

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: A neural network 80 for aligning a source word in a source sentence to a word or words in a target sentence parallel to the source sentence, includes: an input layer 90 to receive an input vector 82. The input vector includes an m-word source context 50 of the source word, n?1 target history words 52, and a current target word 98 in the target sentence. The neural network 80 further includes: a hidden layer 92 and an output layer 94 for calculating and outputting a probability as an output 96 of the current target word 98 being a translation of the source word.

Abstract: A lead-free steel for machine structural use with excellent machinability and low strength an isotropy, which does not contain Pb and is equal to or higher than a conventional D Pb-containing free cutting steel in properties, is provided. This steel includes, on the weight basis, C: 0.10 to 0.65%; Si: 0.03 to 1.00%; Mn: 0.30 to 2.50%; S: 0.03 to 0.35%; Cr: 0.1 to 2.0%; Al: less than 0.010%; Ca: 0.0005 to 0.020%; Mg: 0.0003 to 0.020%; 0: less than 20 ppm; and the balance being Fe and inevitable impurities.

Abstract: A lead-free steel for machine structural use with excellent machinability and low strength anisotropy, which does not contain Pb and is equal to or higher than a conventional Pb-containing free cutting steel in properties, is provided. This steel includes, on the weight basis, C: 0.10 to 0.65%; Si: 0.03 to 1.00%; Mn: 0.30 to 2.50%; S: 0.03 to 0.35%; Cr: 0.1 to 2.0%; Al: less than 0.010%; Ca: 0.0005 to 0.020%; Mg: 0.0003 to 0.020%; O: less than 20 ppm; and the balance being Fe and inevitable impurities.

Abstract: A lead-free steel for machine structural use with excellent machinability and low strength an isotropy, which does not contain Pb and is equal to or higher than a conventional D Pb-containing free cutting steel in properties, is provided. This steel includes, on the weight basis, C: 0.10 to 0.65%; Si: 0.03 to 1.00%; Mn: 0.30 to 2.50%; S: 0.03 to 0.35%; Cr: 0.1 to 2.0%; Al: less than 0.010%; Ca: 0.0005 to 0.020%; Mg: 0.0003 to 0.020%; 0: less than 20 ppm; and the balance being Fe and inevitable impurities.

Abstract: A miniaturized optical disc memory is receivable in a slot, of about 17 mm height, normally accommodating a floppy disc drive. A base includes a base plate with integral, peripheral sidewalls and an internal lateral partition wall which define a cartridge receiving slot on the upper surface of the base plate. First and second support plates extend from the partition wall to the rear peripheral sidewall of the base and define respective, first and second upper mounting surfaces and lower first and second cavities respectively receiving an ejection motor and a fixed optical system, individual optical components being mounted and aligned on integral, precision machined blocks in the second cavity for transmitting a laser beam and receiving a reflected beam along a central, longitudinal optical axis beneath the base plate.

Abstract: To present appropriate characteristic terms to a searcher with respect to an arbitrary retrieval term, and provide an efficient information retrieving method.

Abstract: A miniaturized optical disc memory is receivable in a slot, of about 17 mm height, normally accommodating a floppy disc drive. A base includes a base plate with integral, peripheral sidewalls and an internal lateral partition wall which define a cartridge receiving slot on the upper surface of the base plate. First and second support plates extend from the partition wall to the rear peripheral sidewall of the base and define respective, first and second upper mounting surfaces and lower first and second cavities respectively receiving an ejection motor and a fixed optical system, individual optical components being mounted and aligned on integral, precision machined blocks in the second cavity for transmitting a laser beam and receiving a reflected beam along a central, longitudinal optical axis beneath the bass plate.

Abstract: A miniaturized optical disc memory is receivable in a slot, of about 17 mm height, normally accommodating a floppy disc drive. A base includes a base plate with integral, peripheral sidewalls and an internal lateral partition wall which define a cartridge receiving slot on the upper surface of the base plate. First and second support plates extend from the partition wall to the rear peripheral sidewall of the base and define respective, first and second upper mounting surfaces and lower first and second cavities respectively receiving an ejection motor and a fixed optical system, individual optical components being mounted and aligned on integral, precision machined blocks in the second cavity for transmitting a laser beam and receiving a reflected beam along a central, longitudinal optical axis beneath the base plate.