Mechanisms are provided for processing sources of content in a corpus of information associated with a domain. The mechanisms ingest a plurality of sources of content in the corpus of information associated with the domain and determine at least one temporal category for the domain based on identification of frequently occurring references to at least one of temporal terms or time spans specified in the plurality of sources of content in the corpus of information associated with the domain. The mechanisms store the at least one temporal category for the domain in association with the domain and process queries applied to the plurality of sources of content in the corpus of information associated with the domain based on the stored at least one temporal category for the domain.

Examples disclosed herein relate to a display of speed reading pattern. Examples include to perform text recognition to recognize text in captured image data, and display the recognized text on a display according to a speed reading pattern. Examples include to determine when the recognized text in the captured image has been displayed via the speed reading pattern, and to provide an indicator to capture additional image data in response to determining the recognized text has been displayed.

Embodiments are directed towards providing a smart sign that dynamically translates content that is displayed on the sign based on a preferred language of mobile devices that are in close proximity to the sign. The smart sign determines when one or more mobile devices are in proximity to the smart sign. The smart sign communicates with each of these mobile devices to determine a preferred language of a respective user of each mobile device. The smart sign translates and displays the content in each of the preferred languages on the sign. In various embodiments, the smart sign can relocate or resize the translated content so that it can fit on a display screen of the smart sign relative to a location of the mobile devices relative to the smart sign.

Methods and systems are provided for improving speech recognition of multilingual named entities. In some embodiments, a list comprising a plurality of named entities may be accessed by a computing device. A first named entity represented in the native language may be compared with the first named entity represented in the foreign language. One or more words that appear in both the first named entity represented in the native language and the first named entity represented in the foreign language may be identified as one or more foreign words. A grapheme-to-phoneme (G2P) conversion may be applied to the one or more foreign words, wherein graphemes of the one or more foreign words are mapped to phonemes in the native language. The G2P conversion may result in a native pronunciation for each of the one or more foreign words, which are added to a recognition dictionary along with the native pronunciations.

A sentence creation system, which outputs an opinion sentence on an agenda, includes: an input unit into which the agenda is input; an agenda analyzing unit analyzing the agenda and judging the polarity of the agenda and a keyword used for searching; a searching unit searching for articles using the keyword and a disputed point word showing a disputed point in the discussion; a disputed point determining unit for determining the disputed point used for creating the opinion sentence; a sentence extracting unit for extracting sentences in which the disputed point is described among the articles output by the searching unit; a sentence sorting unit for creating sentences by sorting the extracted sentences; an evaluating unit for evaluating the sentences; a paraphrasing unit for inserting appropriate conjunctions into the sentences; and an output unit for outputting the most highly evaluated sentence among the plural sentences as the opinion sentence.

A method for providing an original sentence and a translation for the original sentence in a user terminal, includes: presenting, by the user terminal, a plurality of images to a user; verifying, by the user terminal, an image selected by the user among the plurality of images; obtaining, by the user terminal, an original sentence corresponding to the image selected by the user and a translation sentence for the image from a database; and providing, by the user terminal, the original sentence corresponding to the selected image and the translation for the original sentence together with the selected image.

Provided are a method and electronic device for voice translation. The electronic device includes a voice receiver configured to receive a voice signal; a processor configured to divide the voice signal into a plurality of voice segments, determine an input language and a speaker that correspond to each of the plurality of voice segments, determine a translation direction based on the input language and the speaker of the voice segments, and translate the voice segments according to the translation direction to generate a translation result; and an output device configured to output the translation result.

A natural language learning method, system, and non-transitory computer readable medium include analyzing a corpus of sentences stored in a database to identify an internal structure of words in the corpus of sentences, creating a plurality of new words that are a combination of the internal structure of a word of the words in the corpus of sentences and the word, clustering the plurality of new words created by the creating that match into a plurality of cluster groups, filtering the plurality of cluster groups to create a partial set of each of the plurality of cluster groups, and performing word embedding processing on the partial set of each of the plurality of cluster groups to obtain vectors for new words.

A method and apparatus are provided for generating concept hierarchies in response to a user request to produce a hierarchy of concepts from a first concept set by performing a natural language processing (NLP) analysis comparison of the vector representations of the concepts in the first concept set to determine a similarity measure for each pair of distinct concepts Ci and Cj in the first concept set, and to construct therefrom a concept hierarchy based on one or more specified hierarchy parameters and the similarity measure for each pair of distinct concepts Ci and Cj in the first concept set.

A modular system and method for a peer to peer communication solution. The modular method supports browser-to-mobile applications (vice versa) and mobile-to-mobile based applications communication. The modular communication allows users to utilize the solution with each module (block) dedicated to different independent aspects of the service in connection with other users. Content is in blocks that are rearrangeable, dynamic, shareble, custom-oriented based on user interaction. The solution focuses on one page application for ease of use. The communication architecture includes direct peer to peer data channel, utilization of server, and storage of information in database.