Abstract: Disclosed embodiments relate to data management of entity pairs. Techniques can include receiving at least two sets of data and a data management task request with each including a set of entities. Techniques can determine a location of each entity in received data sets in a representative space by determining representative structure of the set of entities. Techniques can then for an entity, a set of representative entity pairs from each set of the at least two sets of data based on how close they are in the representative space. Technique can then analyze the set of representative entity pairs to identify most similar entity pairs include in a set of candidate pairs by determining closeness of location of entities in each entity pair in the representative space. Technique can then determine matched entity pairs of the candidate pairs using a first machine learning model is trained using the candidate pairs by applying labels, and utilizing the matched pairs to perform the requested data management task.

Abstract: Disclosed embodiments relate to generalized entity matching. Techniques can include receiving a data pair of two entities that may be pre-processed to have parsable data structures, and serializing the data pair into a sequence of tokens based on data structure of each entity in the data pair. Techniques can further include encoding the serialized data pair to include topic attributes that may be mapped to data in the data pair and the topic of the mapped data matches the topic represented by topic attribute and the data in the data pair is concatenated. Techniques can further include pooling attributes in the data pair based on contextualized attributed representations of each encoded entity in the data pair and schema of each entity of the data pairs, where the contextual attribute representations are based on a first token of each encoded attribute in the sequence of tokens, and predicting matching labels between the data pairs based on pooled attributes.

Abstract: Disclosed embodiments relate to aligning pairs of sentences. Techniques can include receiving a plurality of sentences; generating a graph for each of at least two sentences of the plurality of sentences, wherein generating a graph for each sentence of the at least two sentences comprises: identifying one or more tokens for the sentence; and connecting via edges the one or more tokens; generating a combined graph for the at least two sentences wherein generating a combined graph comprises: aligning the identified tokens of the at least two sentences of the plurality of sentences; identifying matching and non-matching tokens between the at least two sentences based on the alignment; and merging matching tokens into a combined graph node.

Abstract: Disclosed embodiments relate to natural language processing. Techniques can include obtaining an encoding model, obtaining a first sentence in a first language and a label associated with the first sentence, obtaining a second sentence in a second language, encoding the first sentence and second sentence using the encoding model, determining the intent of the first encoded sentence, determining the language of the first encoded sentence and the language of the second encoded sentence, and updating the encoding model based on the determined intent of the first encoded sentence, the label, the determined language of the first encoded sentence, and the determined language of the second encoded sentence.

Abstract: Disclosed embodiments relate to entity set expansion to associate with a text corpus. Techniques can include receiving unstructured data and a set of concepts associated with the data to determine, using a language model, a set of candidate entities in the data associated with the set of concepts, wherein the association is measured based on the relevancy of each candidate entity of the set of candidate entities to context of the data. Techniques can then determine, using a plurality of methods, associations between each candidate entity in the set of candidate entities and each concept in the concept of the set of concepts, wherein the each candidate entity is assigned a rank for each method of the plurality of methods. Techniques can use the assigned ranks to determine a combined rank of the each candidate entity of the set of candidate entities, wherein the combined rank of the each candidate entity is based on the assigned rank of the each candidate entity for the each method of the plurality of methods.

Abstract: Disclosed embodiments relate to systems, methods, and computer readable storage media for performing dataset discovery. Some embodiments may include accessing a data repository having a plurality of tables having cell values arranged in one or more columns and one or more rows, generating serialized sequences of the cell values that correspond to particular columns of the plurality of tables, inputting the serialized sequences into a natural language model, converting, using the natural language model, the serialized sequences into contextualized embeddings associated with the plurality of tables, storing the contextualized embeddings associated with the plurality of tables in one or more vector indices, receiving a query table, or generating an output of one or more candidate tables from the plurality of tables that are unionable with the received query table.

Abstract: Disclosed embodiments relate to extracting classification information from input text.

Abstract: Disclosed embodiments relate to extracting classification information from input text.

Abstract: Disclosed embodiments relate to natural language processing. Techniques can include receiving input text, extracting, from the input text, at least one modifier and aspect pair, receiving data from a knowledgebase, based on the at least one modifier and aspect pair and commonsense data, generate one or more premise embeddings, convert the input text into tokens, generating at least one vector for one or more of the tokens based on an analysis of the tokens, combine the at least one vector with the one or more premise embeddings to create at least one combined vector, and analyze the at least one combined vector wherein the analysis generates an output indicative of a feature of the input text.

Abstract: Disclosed embodiments relate to aligning pairs of sentences. Techniques can include receiving a plurality of sentences; generating a graph for each of at least two sentences of the plurality of sentences, wherein generating a graph for each sentence of the at least two sentences comprises: identifying one or more tokens for the sentence; and connecting via edges the one or more tokens; generating a combined graph for the at least two sentences wherein generating a combined graph comprises: aligning the identified tokens of the at least two sentences of the plurality of sentences; identifying matching and non-matching tokens between the at least two sentences based on the alignment; and merging matching tokens into a combined graph node.

Abstract: Disclosed embodiments relate to aligning pairs of sentences. Techniques can include receiving a plurality of sentences; generating a graph for each of at least two sentences of the plurality of sentences, wherein generating a graph for each sentence of the at least two sentences comprises: identifying one or more tokens for the sentence; and connecting via edges the one or more tokens; generating a combined graph for the at least two sentences wherein generating a combined graph comprises: aligning the identified tokens of the at least two sentences of the plurality of sentences; identifying matching and non-matching tokens between the at least two sentences based on the alignment; and merging matching tokens into a combined graph node.

Abstract: Disclosed embodiments relate to natural language processing. Techniques can include receiving input text, extracting, from the input text, at least one modifier and aspect pair, receiving data from a knowledgebase, based on the at least one modifier and aspect pair and commonsense data, generate one or more premise embeddings, convert the input text into tokens, generating at least one vector for one or more of the tokens based on an analysis of the tokens, combine the at least one vector with the one or more premise embeddings to create at least one combined vector, and analyze the at least one combined vector wherein the analysis generates an output indicative of a feature of the input text.

Abstract: Based on an idea that there is a correlation between the number of mobile terminals 300 detected inside a facility (that is, a detected terminal count) and visitors of the facility, the number of users using the facility (that is, a crowd condition of the facility) is estimated using a WiFi function provided in the mobile terminals 300. Consequently, the crowd condition of the facility can simply be estimated while costs are suppressed to be low, compared to conventional methods in which, e.g., infrared modules or Web cameras are provided at entrances/exits of a facility to estimate a crowd condition.

Abstract: A suspicious person detection technology which is less likely to cause a blind spot of detection of a suspicious person is provided. A suspicious person detection system detects a suspicious person present in a predetermined area and includes a probe request detection terminal (100) configured to detect a probe request transmitted from a mobile terminal (400) to generate probe information including first identification information specific to the mobile terminal which transmits the probe information, and an analyzing apparatus (200) configured to acquire the probe information from the probe request detection terminal, and, in the case where the first identification information included in the probe information matches none of one or more pieces of second identification information set in advance, transmit suspicious person information indicating that a suspicious person is detected to a predetermined information processing apparatus (300).