Abstract: A model learning apparatus of the present invention has a question/answer-pair expansion unit and a translation-model learning unit. The question/answer-pair expansion unit generates expansion question/answer pairs by increasing the number of question/answer pairs associated with an index indicating that it sounds more like the character. The translation-model learning unit learns a translation model and a reverse translation model by using the expansion question/answer pairs. A response selecting apparatus of the present invention has a record unit, a document search unit, a score calculation unit, and a ranking unit. The record unit records question/answer pairs and the above described learned translation model. The score calculation unit obtains a translation likelihood which is a numerical value based on the probability of obtaining the answer from the input question and calculates a score of each of a search-result question/answer pair with respect to the input question.

Abstract: Provided is a technique for generating an utterance based on data indicating the context of a dialogue.

Abstract: A position detection device includes two detection systems that are respectively fed from power supply systems different from each other, and displace together with a shift lever. Each detection system can output detection patterns with four digits. A detection pattern when being located at a given position is different from a detection pattern when being located at another position. In any detection pattern, outputs of certain two digits among the four digits are set so as to be identical to each other, and to be different from outputs of two other digits. Alternatively, outputs of certain three digits among the four digits are set to be identical to each other, and to be different from an output of another digit.

Abstract: Provided is a technique for generating a tagging model for attaching a tag in consideration of a phrase based on dependency between words. A tagging model generation apparatus includes a learning section 2 which generates, by using inputted learning data, a tagging model including probability-related information serving as information related to the probability that each tag is associated with each word-related information, and joint probability-related information serving as information related to a joint probability which serves as the probability of appearance of each tag in which appearance frequencies of a plurality of consecutive tags associated with pieces of word-related information of a plurality of consecutive words in each text are taken into consideration, and a storage section 3 which stores the generated tagging model.

Abstract: An extended role play-based utterance set generation apparatus includes a first data store storing role play-based utterance sets and a second data store storing non-role-played utterance sets. The role play-based utterance sets include a first query and a role play-based response to the query. The non-role-played utterance sets include a second query and a non-role-played response to the query. The disclosed technology determines similarity between the role play-based response and the non-role-played response. Upon determining that the role play-based response is the same or similar to the non-role-played response, the disclosed technology generates an association between the role play-based response and the second query and extends the role play-based utterance sets in the first data store with the second query.

Abstract: An object is to give the user the impression that the system has sufficient dialogue capabilities. A humanoid robot (50) presents a first system speech to elicit information regarding a user's experience in a subject contained in a dialogue. A microphone (11) accepts a first user speech spoken by a user (101) after the first system speech has been spoken. When the first user speech is a speech that contains information regarding the user's experience, the humanoid robot (50) presents a second system speech to elicit information regarding the user's evaluation of the user's experience. The microphone (11) accepts a second user speech spoken by the user (101) after the second system speech has been spoken. When the second user speech is a speech that contains the user's positive or negative evaluation, the humanoid robot (50) presents a third system speech to sympathizes with the positive or negative evaluation.

Abstract: An object is to give the user the impression that the system has sufficient dialogue capabilities. A dialogue system (100) has a personality virtually set thereto. A microphone (11) collects a spoken voice of a user (101) and converts it into a voice signal. A voice recognition unit (20) performs voice recognition on the voice signal of the spoken voice of the user (101) to convert the voice signal into a text that represents the content of the user's speech. A speech determination unit (30) determines a text representing the content of a system speech that is based at least on information contained in the most recently input user speech and information set to the personality of the dialogue system. The voice synthesis unit (40) converts the text representing the content of the system speech into a voice signal representing the content of the system speech. A speaker (51) outputs the voice signal representing the content of the system speech.

Abstract: A lever input device includes: a lever which is tiltable in a first direction orthogonal to an axis of the lever about the axis due to an operation by a user; a swing arm which engages with the lever and swings along with the tilting of the lever in the first direction and amplifies a displacement amount of the lever at the time of tilting; and a magnet body mounted on the swing arm, wherein the swing arm is elongated along a second direction which is a direction along the axis, is configured such that distance (D13) between a swing fulcrum and a mounting portion of the magnet body becomes larger than distance (D12) between the swing fulcrum of the swing arm and an engaging portion of the swing arm with the lever.

Abstract: A response selecting apparatus includes a recording part, a document searching part, an information acquiring part, a score calculating part, and a ranking part. The document searching part searches for a question-answer pair from the question-answer pairs recorded in the recording part using the input question as input. The information acquiring part acquires information for quantifying appropriateness of the search-result-question-answer pair with respect to the input question using the input question and the search-result-question-answer pair as input. The score calculating part calculates a score with respect to the input question for each of the search-result-question-answer pairs from a numerical value indicating appropriateness based on a search scheme and a numerical value based on the quantification information.

Abstract: An extended role play-based utterance set generation apparatus includes a first storage part 1 in which I role play-based utterance sets i=(ti(1), ti(2)) (i=1, . . . , I) are stored, a second storage part 2 in which J non-role-played utterance sets j=(t?j(1), t?j(2)) (j=1, . . . , J) are stored, a non-role-played utterance set selecting part 3 configured to select from the second storage part 2, one or more non-role-played utterance sets j corresponding to the second utterance t?j(2) which is the same as or similar to the second utterance ti(2) of each of the role play-based utterance sets i read from the first storage part 1, and an extended role play-based utterance set generating part 4 configured to associate the first utterance t?j(1) of each of the selected non-role-played utterance sets j with the second utterance ti(2) of each of the role play-based utterance sets i to make an extended role play-based utterance set.

Abstract: A model learning apparatus of the present invention has a question/answer-pair expansion unit and a translation-model learning unit. The question/answer-pair expansion unit generates expansion question/answer pairs by increasing the number of question/answer pairs associated with an index indicating that it sounds more like the character. The translation-model learning unit learns a translation model and a reverse translation model by using the expansion question/answer pairs. A response selecting apparatus of the present invention has a record unit, a document search unit, a score calculation unit, and a ranking unit. The record unit records question/answer pairs and the above described learned translation model. The score calculation unit obtains a translation likelihood which is a numerical value based on the probability of obtaining the answer from the input question and calculates a score of each of a search-result question/answer pair with respect to the input question.

Abstract: Provided is a technique for generating a tagging model for attaching a tag in consideration of a phrase based on dependency between words. A tagging model generation apparatus includes a learning section 2 which generates, by using inputted learning data, a tagging model including probability-related information serving as information related to the probability that each tag is associated with each word-related information, and joint probability-related information serving as information related to a joint probability which serves as the probability of appearance of each tag in which appearance frequencies of a plurality of consecutive tags associated with pieces of word-related information of a plurality of consecutive words in each text are taken into consideration, and a storage section 3 which stores the generated tagging model.

Abstract: An input device includes: an operating unit that is operated by a user; a detent pin that is displaceable along with an operation of the operating unit; a columnar detent member where a spiral groove about a predetermined axis A is formed on an outer peripheral surface of the detent member that is contact with the detent pin; and a motor (rotary driving part) that rotates the detent member about axis A.

Abstract: An input device includes a knob, a detector, an electromagnetic brake, an elastic member, and a controller. The detector detects a rotation angle of the knob. The electromagnetic brake regulates rotation of the knob. The elastic member is provided between the knob and the electromagnetic brake. When the current position of the knob in the circumferential direction is not the target position for rotation regulation of the knob, the controller does not activate the electromagnetic brake. When the current position of the knob in the circumferential direction is the target position for rotation regulation of the knob, the controller determines whether to regulate rotation of the knob based on a rotation direction of the knob, or on a rotation angle of the knob that shifts from the holding position of the knob in the circumferential direction due to deformation of the elastic member.

Abstract: A lever input device includes: a lever which is tiltable in a first direction orthogonal to an axis of the lever about the axis due to an operation by a user; a swing arm which engages with the lever and swings along with the tilting of the lever in the first direction and amplifies a displacement amount of the lever at the time of tilting; and a magnet body mounted on the swing arm, wherein the swing arm is elongated along a second direction which is a direction along the axis, is configured such that distance (D13) between a swing fulcrum and a mounting portion of the magnet body becomes larger than distance (D12) between the swing fulcrum of the swing arm and an engaging portion of the swing arm with the lever.

Abstract: A position detection device includes two detection systems that are respectively fed from power supply systems different from each other, and displace together with a shift lever. Each detection system can output detection patterns with four digits. A detection pattern when being located at a given position is different from a detection pattern when being located at another position. In any detection pattern, outputs of certain two digits among the four digits are set so as to be identical to each other, and to be different from outputs of two other digits. Alternatively, outputs of certain three digits among the four digits are set to be identical to each other, and to be different from an output of another digit.

Abstract: The present disclosure provides an input device that puts signals into equipment in response to turning action and that can come down in thickness along an axis of a rotary shaft. The input device includes a knob configured to be turned, a rotary shaft configured to turn together with the knob, and a flange disposed around an outer peripheral surface of the rotary shaft. The flange is designed to regulate turning of the rotary shaft. The input device further includes an elastic component that is disposed around the outer peripheral surface of the rotary shaft and is fastened to the flange, a rotation controller that permits or inhibits turning of the elastic component, and a detector that detects a rotational state of the rotary shaft.

Abstract: An input device includes: an operating unit that is operated by a user; a detent pin that is displaceable along with an operation of the operating unit; a columnar detent member where a spiral groove about a predetermined axis A is formed on an outer peripheral surface of the detent member that is contact with the detent pin; and a motor (rotary driving part) that rotates the detent member about axis A.

Abstract: An input device includes a knob, a detector, an electromagnetic brake, an elastic member, and a controller. The detector detects a rotation angle of the knob. The electromagnetic brake regulates rotation of the knob. The elastic member is provided between the knob and the electromagnetic brake. When the current position of the knob in the circumferential direction is not the target position for rotation regulation of the knob, the controller does not activate the electromagnetic brake. When the current position of the knob in the circumferential direction is the target position for rotation regulation of the knob, the controller determines whether to regulate rotation of the knob based on a rotation direction of the knob, or on a rotation angle of the knob that shifts from the holding position of the knob in the circumferential direction due to deformation of the elastic member.

Abstract: The present disclosure provides an input device that puts signals into equipment in response to turning action and that can come down in thickness along an axis of a rotary shaft. The input device includes a knob configured to be turned, a rotary shaft configured to turn together with the knob, and a flange disposed around an outer peripheral surface of the rotary shaft. The flange is designed to regulate turning of the rotary shaft. The input device further includes an elastic component that is disposed around the outer peripheral surface of the rotary shaft and is fastened to the flange, a rotation controller that permits or inhibits turning of the elastic component, and a detector that detects a rotational state of the rotary shaft.