Abstract: An approach for generating synthetic treebanks to be used in training a parser in a production system is provided. A processor receives a request to generate one or more synthetic treebanks from a production system, wherein the request indicates a language for the one or more synthetic treebanks. A processor retrieves at least one corpus of text in which the requested language is present. A processor provides the at least one corpus to a transformer enhanced parser neural network model. A processor generates at least one synthetic treebank associated with a string of text from the at least one corpus of text in which the requested language is present. A processor sends the at least one synthetic treebank to the production system, wherein the production system trains a parser utilized by the production system with the at least one synthetic treebank.

Abstract: A method is provided for dictionary expansion. The method acquires an object from a user and adds the object to a set of objects previously acquired from the user that form an expandable dictionary. The method calculates a centroid based on the set. The method calculates a similarity score of each of a plurality of objects relative to the centroid for each of a plurality of object features to calculate a weighted sum of similarity scores for each of the plurality of objects. The method presents candidate objects selected among the plurality of objects based on the weighted sum. The method acquires, from the user, a preferred candidate object among the candidate objects. The method updates weights of the plurality of features to maximize the weighed sum of similarity scores for the preferred candidate object. The method expands the dictionary by adding the preferred candidate object to the expandable dictionary.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: A computer-implemented method for extracting semantic relations is disclosed. In the method, a plurality of hierarchal structures that originates from a corpus of documents is obtained. Each hierarchal structure includes a plurality of elements having respective recitations included in a corresponding document. In the method, for each predetermined relationship between ancestor and descendant elements in the hierarchal structures, a first keyword list is extracted from the ancestor element and a second keyword list is extracted from the descendant element. A statistical index is calculated for each pair of first and second keywords using the first keyword lists and the second keyword lists. The index indicates a strength of association between the first and second keywords. In the method, a candidate list of keyword pairs having semantic relationships is output using the statistical index calculated for each pair.

Abstract: An approach for generating synthetic treebanks to be used in training a parser in a production system is provided. A processor receives a request to generate one or more synthetic treebanks from a production system, wherein the request indicates a language for the one or more synthetic treebanks. A processor retrieves at least one corpus of text in which the requested language is present. A processor provides the at least one corpus to a transformer enhanced parser neural network model. A processor generates at least one synthetic treebank associated with a string of text from the at least one corpus of text in which the requested language is present. A processor sends the at least one synthetic treebank to the production system, wherein the production system trains a parser utilized by the production system with the at least one synthetic treebank.

Abstract: A polyurethane resin composition includes a reaction product of a polyisocyanate component and a polyol component, and a wax. The polyisocyanate component contains a highly symmetrical polyisocyanate. The polyol component contains a polycarbonate polyol having a number average molecular weight of 600 or more and 1200 or less and a polyester polyol having a number average molecular weight of 600 or more and 1200 or less. A ratio of the polycarbonate polyol is 3 parts by mass or more and 40 parts by mass or less, and a ratio of the polyester polyol is 60 parts by mass or more and 97 parts by mass or less with respect to 100 parts by mass of the total amount of the polycarbonate polyol and the polyester polyol.

Abstract: The polyurethane resin composition contains, a polyisocyanate component containing p-MDI, a polyol component, an organic metal catalyst, and a reaction retardant represented by general formula (1) below, wherein the mole ratio of the reaction retardant relative to 1 mol of the organic metal catalyst is 0.50 or more and 2.50 or less. (in general formula (1), A represents an aliphatic ring or an aromatic ring, R1 represents a hydrocarbon group composing ring A, R2 represents an aliphatic hydrocarbon group bonded to ring A. R3 represents a hydrogen atom or alkyl group bonded to nitrogen atom included in ring A. R1 represents a hydrogen atom or carboxyl group bonded to ring A. m is 1 or 2, n is 0 or 1, and total of n and no is 2 or less.

Abstract: A polyurethane resin is a reaction product of a polyisocyanate component containing a bis(isocyanatomethyl)cyclohexane with a macropolyol component having a number average molecular weight of above 400 and 5000 or less. The shore A hardness thereof is 80 or less, a temperature at which a storage elastic modulus E? thereof shows 1×106 Pa is 200° C. or more, and a ratio (E?150/E?50) of a storage elastic modulus E?150 at 150° C. with respect to a storage elastic modulus E?50 at 50° C. is 0.1 or more and 1.4 or less.

Abstract: A computer-implemented method is provided. The method includes acquiring a seed word; calculating a similarity score of each of a plurality of words relative to the seed word for each of a plurality of models to calculate a weighted sum of similarity scores for each of the plurality of words; outputting a plurality of candidate words among the plurality of words; acquiring annotations indicating at least one of preferred words and non-preferred words among the plurality of the candidate words; updating weights of the plurality of models in a manner to cause weighted sums of similarity scores for the preferred words to be relatively larger than the weighted sums of the similarity scores for the non-preferred words, based on the annotations; and grouping the plurality of candidate words output based on the weighted sum of similarity scores calculated with updated weights of the plurality of models.

Abstract: A simulated sclera 2 is obtained by including a plurality of fiber layers (a) and a resin (b) in contact with the fiber layer (a), having a. fiber diameter of a fiber constituting the fiber layer (a) of 0.6 ?m or more and 170.0 ?m or less, laminating the plurality of fiber layers (a), and impregnating the laminated fiber layers (a) with the resin (b).

Abstract: A method is provided for dictionary expansion. The method acquires an object from a user and adds the object to a set of objects previously acquired from the user that form an expandable dictionary. The method calculates a centroid based on the set. The method calculates a similarity score of each of a plurality of objects relative to the centroid for each of a plurality of object features to calculate a weighted sum of similarity scores for each of the plurality of objects. The method presents candidate objects selected among the plurality of objects based on the weighted sum. The method acquires, from the user, a preferred candidate object among the candidate objects. The method updates weights of the plurality of features to maximize the weighed sum of similarity scores for the preferred candidate object. The method expands the dictionary by adding the preferred candidate object to the expandable dictionary.

Abstract: A computer-implemented method, computer program product, and system are provided for providing a recommendation. The method includes receiving, by a conversation system, a query from a user. The method also includes inputting the query into an intent-entity model to obtain a first output. The method further includes inputting the query into a question-answering system to obtain a second output. The method additionally includes analyzing the first output from the intent-entity model to calculate a value of degree of ambiguity of the first output to the query. The method also includes analyzing the query and the second output from the question-answering system to calculate a value of extent of satisfaction to which the second output satisfies the query. The method further includes determining one or more recommendations using the degree of ambiguity and the extent of satisfaction. The method additionally includes outputting the one or more recommendations to the user.

Abstract: A polyurethane gel material includes an aliphatic polyisocyanate (A) having an average functionality of 2.3 or more and 3.2 or less, a polyol (B) having an average functionality of 2.0 or more and 2.3 or less, and a plasticizer (C) having an ester group. The aliphatic polyisocyanate (A) contains an isocyanurate derivative of an aliphatic diisocyanate and/or an alcoholic modified isocyanurate derivative of an aliphatic diisocyanate. The polyol (B) contains a polyoxypropylene polyol and/or a polytetramethylene ether glycol. The polyol (B) has an average hydroxyl value of 73 mgKOH/g or more and 200 mgKOH/g or less. A ratio of the plasticizer (C) per 100 parts by mass of the polyol component (B) is 100 parts by mass or more and 500 parts by mass or less.

Abstract: A polyurethane gel material includes an aliphatic polyisocyanate (A) having an average functionality of 2.3 or more and 3.2 or less, a polyol (B) having an average functionality of 2.0 or more and 2.3 or less, and a plasticizer (C) having an ester group. The aliphatic polyisocyanate (A) contains an isocyanurate derivative of an aliphatic diisocyanate and/or an alcoholic modified isocyanurate derivative of an aliphatic diisocyanate. The polyol (B) contains a polyoxyalkylene (carbon number of 2 to 3) polyol having an ethylene oxide content of 30% by mass or less, and/or a polytetramethylene ether glycol. The polyol (B) has an average hydroxyl value of 30 mgKOH/g or more and 70 mgKOH/g or less. A ratio of the plasticizer (C) per 100 parts by mass of the polyol component (B) is 50 parts by mass or more and 400 parts by mass or less.

Abstract: A buffer material including a skinned polyurethane foam including a foam layer and a skin layer formed on the surface of the foam layer, wherein the skinned polyurethane foam essentially contains no silicone compound, the foam layer is polyurethane foam, the skin layer is a polyurethane resin layer produced by reaction of a skin-isocyanate component containing an aliphatic and/or an alicyclic polyisocyanate with a skin-active hydrogen group-containing component, the skin layer has a storage modulus at 23° C. (E?coat) of 1×107 Pa or more and 3×108 Pa or less, the foam layer has a storage modulus at 23° C. (E?foam) of 1×105 Pa or more and 5×106 Pa or less, and the ratio (E?coat/E?foam) of the storage modulus at 23° C. (E?coat) of the skin layer relative to the storage modulus at 23° C. (E?foam) of the foam layer is 10 or more and 500 or less.

Abstract: A computer-implemented method is provided. The method includes acquiring a seed word; calculating a similarity score of each of a plurality of words relative to the seed word for each of a plurality of models to calculate a weighted sum of similarity scores for each of the plurality of words; outputting a plurality of candidate words among the plurality of words; acquiring annotations indicating at least one of preferred words and non-preferred words among the plurality of the candidate words; updating weights of the plurality of models in a manner to cause weighted sums of similarity scores for the preferred words to be relatively larger than the weighted sums of the similarity scores for the non-preferred words, based on the annotations; and grouping the plurality of candidate words output based on the weighted sum of similarity scores calculated with updated weights of the plurality of models.

Abstract: A method of question answering from multilingual information sources is disclosed. The present invention discloses a method, a computer system and a program product for selecting an information source language of an information source, the method includes: receiving a question; analyzing the question to obtain a category information of a word included in the question; obtaining a word included in the category information as estimated topic or region related to the question; determining a candidate for an information source language using the estimated topic or region; and selecting the information source language and corresponding information sources for retrieving documents to generate an answer of the question.

Abstract: The polyurethane resin composition contains a polyisocyanate component containing p-MDI, a polyol component, an organic metal catalyst, and a reaction retardant represented by general formula (1) below, wherein the mole ratio of the reaction retardant relative to 1 mol of the organic metal catalyst is 0.50 or more and 2.50 or less, (in general formula (1), A represents an aliphatic ring or an aromatic ring. R1 represents a hydrocarbon group composing ring A. R2 represents an aliphatic hydrocarbon group bonded to ring A. R3 represents a hydrogen atom or alkyl group bonded to nitrogen atom included in ring A. R4 represents a hydrogen atom or carboxyl group bonded to ring A. m is 1 or 2, n is 0 or 1, and total of n and m is 2 or less.

Abstract: A polyurethane resin is a reaction product of a polyisocyanate component containing a bis(isocyanatomethyl)cyclohexane with a macropolyol component having a number average molecular weight of above 400 and 5000 or less. The shore A hardness thereof is 80 or less, a temperature at which a storage elastic modulus E? thereof shows 1×106 Pa is 200° C. or more, and a ratio (E?150/E?50) of a storage elastic modulus E?150 at 150° C. with respect to a storage elastic modulus E?50 at 50° C. is 0.1 or more and 1.4 or less.