Abstract: A question-answering apparatus includes answer generating means of accepting as input a document set made up of one or more documents, a question sentence, and a style of an answer sentence for the question sentence and running a process of generating an answer sentence for the question sentence using a learned model based on the document set, wherein the learned model determines probability of generation of words contained in the answer sentence, according to the style, when generating the answer sentence.

Abstract: Provided is an information processing apparatus capable of acquiring a second inspection program capable of determining whether it is appropriate to cause a first inspection program, which has undergone machine learning so that acceptance of an acceptable image/unacceptable image may be determined, to determine acceptance of an unknown image. The information processing apparatus ranks, for pseudo pair images including acceptable images and unacceptable images obtained by performing pseudo image generation processing on determined pair images including acceptable images and unacceptable images, the pseudo pair images according to correctness of the acceptance determination by the first inspection program for each pair on the basis of results of the acceptance determination by the first inspection program, and by causing a mathematical model to undergo second machine learning that uses the determined pair images and a predetermined number or more of the ranked pseudo pair images as inputs.

Abstract: It is intended to allow learning of a spoken sentence generation model for generating a spoken sentence which enables a discussion covering a wide range of topics. A discussion data storage unit 100 stores a plurality of discussion data sets each including a discussion spoken sentence indicating a discussion topic and a pair of an approving spoken sentence indicating approval for the discussion spoken sentence and a disapproving spoken sentence indicating disapproval for the discussion spoken sentence.

Abstract: An encoding unit transforms a piece of text divided into a plurality of spans that are subdivided units of the piece of text and a question which have been input into a vector representation sequence representing a meaning of a span and the question based on the piece of text and the question which have been input using a pre-trained encoding model for transforming input text into a vector representation sequence representing a meaning of the input text. For each of the spans, an evidence extraction unit estimates an evidence score indicating the degree to which the span is suitable as the evidence for extracting the answer using a pre-trained extraction model for calculating the evidence score based on the vector representation sequence.

Abstract: There is provided a learning device for learning a neural network used for search of external knowledge in order to increase search accuracy of external knowledge required for arithmetic processing. With an input sentence Q as an input, an external knowledge search unit 22 selects pieces of external knowledge based on similarity degrees between pieces of external knowledge included in an external knowledge database 2 and the input sentence Q, using a neural network, and causes the selected pieces of external knowledge to be search results R2. A processing unit 14 acquires a response sentence A to the input sentence Q by arithmetic processing with the input sentence Q and the selected pieces of external knowledge as an input. A consideration calculation unit 23 calculates a consideration v determined from an index indicating correctness of the response sentence A based on a true output T given to the input sentence Q in advance and an index indicating quality of the selected pieces of external knowledge.

Abstract: A nonverbal information generation apparatus includes a nonverbal information generation unit that generates nonverbal information that corresponds to feature quantities of voice or text on the basis of the feature quantities and a learned nonverbal information general model. The nonverbal information is information for controlling an expression unit that expresses behavior so that at least one of the number of times that the behavior is performed and the magnitude of the behavior correspond to the feature quantities.

Abstract: An information processing device includes a processing unit configured to receive as input a document and a question, and to execute processing to output an answer range as a range of a string that can be an answer to the question in the document, or an answer suitability of the document with respect to the question, by using neural networks, wherein the processing unit includes a first neural network configured to calculate the answer range, and a second neural network configured to calculate the answer suitability, and between the first neural network and the second neural network, part of layers constituting both neural networks is shared.

Abstract: To make it possible to generate dialogue data for generating a question sentence to deeply delve conversation at a low cost. For each of a plurality of pieces of data each including a set of a first utterance sentence that is a sentence uttered by a first user, a second utterance sentence that is a sentence uttered by a second user and is a response to the first utterance sentence, and a third utterance sentence that is a sentence uttered by the first user and is a response to the second utterance sentence, a dialogue data generation unit 110 generates a set of the first utterance sentence of the data and the second utterance sentence of the data as dialogue data when the second utterance sentence of the data is a question sentence using an interrogative.

Abstract: There is provided a processing device for natural language processing with high search accuracy while time complexity and space complexity are suppressed. A first external knowledge search unit 11 acquires pieces of external knowledge searched for based on first scores obtained based on similarity degrees between pieces of external knowledge included in an external knowledge database 2 and an input sentence as first search results R1, with the input sentence Q as an input; and a second external knowledge search unit 12 determines second scores obtained from similarity degrees between pieces of external knowledge included in the first search results R1 and the input sentence using a neural network, and searches the first search results R1 to acquire second search results. A processing unit 14 acquires an output to the input sentence by arithmetic processing with the input sentence and pieces of external knowledge included in the second search results R2 as an input.

Abstract: The present invention makes it possible to generate a paraphrastic sentence that has a similar meaning to the original sentence despite a local word/phrase difference, or a non-paraphrastic sentence that is not a paraphrase despite having a similar meaning to the original sentence in terms of the entire sentence. An estimation unit 22 estimates a word deletion probability for each of words constituting an input sentence, by using a positive example model that has been trained based on a positive example constituted by a sentence and a paraphrastic sentence of the sentence, and is used to generate a paraphrastic sentence by deleting a word, or by using a negative example model that has been trained based on a negative example constituted by the sentence and a non-paraphrastic sentence of the sentence, and is used to generate a non-paraphrastic sentence by deleting a word.

Abstract: This disclosure is provided, in which an answer generation unit configured to receive a document and a question as inputs, and execute processing of generating an answer sentence for the question by a learned model by using a word included in a union of a predetermined first vocabulary and a second vocabulary composed of words included in the document and the question, in which the learned model includes a learned neural network that has been learned in advance whether word included in the answer sentence is included in the second vocabulary, and increases or decreases a probability at which a word included in the second vocabulary is selected as the word included in the answer sentence at the time of generating the answer sentence by the learned neural network.

Abstract: A question generation device includes: generating means which uses a query and a relevant document including an answer to the query as input and, using a machine learning model having been learned in advance, generates a revised query in which a potentially defective portion of the query is supplemented with a word included in a prescribed lexical set.

Abstract: An argumentation structure can be automatically extended. A template creation unit 22 creates a template using a predetermined rewriting pattern by receiving, as an input, a proposition represented by each of nodes in an argumentation structure including the nodes respectively representing a main proposition of argumentation and a proposition that functions as an argument for another proposition. An additional proposition output unit 28 creates a proposition functioning as an argument for the input proposition using the created template and outputs the created proposition as a proposition represented by a node to be added to the argumentation structure.

Abstract: A communication skill evaluation system including: an audio input device; a measurement device; an utterance period detection unit that, based on the audio information input by the audio input device, detects an utterance period and a participant who spoke in each utterance period; a participatory role assignment unit that assigns a participatory role to each participant in accordance with whether or not each participant spoke in each utterance pair composed of two utterances obtained in chronological order from each utterance period; a feature quantity extraction unit that, based on the measurement results by the measurement device, extracts a non-verbal feature quantity for each participant, relating to the non-verbal action at the end of the utterance in each utterance period; and an estimation unit that estimates communication skill for each participant based on a combination, in each utterance period, of the participatory role and the non-verbal feature quantity.

Abstract: A question that can be answered with polarity can be accurately answered with polarity. A machine comprehension unit 210 estimates the start and the end of a range serving as a basis for an answer to the question in text by using a reading comprehension model trained in advance to estimate the range based on the inputted text and question. A determination unit 220 determines the polarity of the answer to the question by using a determination model trained in advance to determine whether the polarity of the answer to the question is positive or not based on information obtained by the processing of the machine comprehension unit 210.

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: It is an object to successfully absorb a difference in characteristics to be taken into consideration between languages and implement common named entity extraction in a processing system.

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: A template creation unit 22 creates a template using a predetermined rewriting pattern by receiving, as an input, a proposition represented by each of nodes in an argumentation structure including the nodes respectively representing a main proposition of argumentation and a proposition that functions as an argument for another proposition. An additional proposition output unit 28 creates a proposition functioning as an argument for the input proposition using the created template and outputs the created proposition as a proposition represented by a node to be added to the argumentation structure.

Abstract: A relationship between phrases can be accurately estimated without incurring the cost of generating learning data. A learning data generation unit 62 extracts a pair of phrases having a dependency relationship with a segment containing a predetermined connection expression representing a relationship between phrases based on a dependency analysis result for input text, and generates a triple consisting of the extracted pair of phrases, and the connection expression or a relation label indicating a relationship represented by the connection expression. A learning unit 63 learns the relationship estimation model for estimating a relationship between phrases based on the triple generated by the learning data generation unit.