Abstract: A plurality of utterances of a first user from the language of the first user is translated into a language of a second user. The confidence scores associated with the translated utterances are compared with a confidence threshold. A predetermined utterance gap is adjusted based on the comparison. The predetermined utterance gap is a duration of time that occurs between utterances.

Abstract: An apparatus, system and method of providing an artificially intelligent (AI) agent capable of assisting information technology (IT) personnel in addressing an IT ticket. The AI agent may include a visualization interface for display capable of receiving dialog from the IT personnel related to the IT ticket; a translation module capable of translating the received dialog to at least one machine language translation; a solutions module capable of receiving the machine language translation, comparing the machine language to a plurality of prospective solutions for IT issues, and selecting a subset of the plurality of prospective solutions deemed most relevant to the IT ticket and returning that subset to the visualization interface; and a feedback module capable of receiving explicit and implied feedback from the IT personal regarding the machine language translation and the selected subset, wherein the selecting of the subset varies upon subsequent received dialog according to the feedback.

Abstract: An adaptive localization system translates and displays translated content to a user, for example through a website or application using the adaptive localization system. A user can view, receive, or otherwise interact with the translated content, which can be differently translated based on desired language, geographic location, an intended user, or other relevant characteristics of the viewing user. The adaptive localization engine can translate the inherent meaning of content rather than, for example, creating an exact grammatical or “word-for-word” translation of individual words or phrases in the content. The adaptive localization engine displays alternate variations of the same translation of content to different users and based on user response to the alternate translations, determines the accuracy or correctness of a certain translations of content and modifies future translations accordingly.

Abstract: Sentence internationalization methods and systems are disclosed.

Abstract: Systems and methods may be used to provide transcription and translation services. A method may include initializing a plurality of user devices with respective language output selections in a translation group by receiving a shared identifier from the plurality of user devices and transcribing the audio stream to transcribed text. The method may include translating the transcribed text to one or more of the respective language output selections when an original language of the transcribed text differs from the one or more of the respective language output selections. The method may include sending, a user device in the translation group, the transcribed text including translated text in a language corresponding to the respective language output selection for the user device. In an example, the method may include customizing the transcription or the translation, such as to a particular topic, location, user, or the like.

Abstract: A method, system, and/or computer program product establish a data organization format for displaying data to a specific user. A first set of data, which is organized according to a user-selected data organization format, is received from a user. A cognition bias, which defines a preferred manner in which the user cognitively interprets data, is identified by being associated with the user-selected data organization format. The cognition bias is also associated with one or more other data organization formats that support the cognition bias. A second set of data is received and formatted using the one or more other data organization formats that also support the cognition bias. The second set of data is then displayed using the one or more data organization formats that also support the cognition bias.

Abstract: A method for automatically translating a banner information, the method may include receiving by a computer the banner information, wherein the banner information is included in at least one banner and describes an identity of a software product; and translating by the computer the banner information into a unique software product identifier using a content of knowledgebase that comprises an attributes schema and translation rules; wherein each software product is associated with a single unique software product identifier; wherein the unique software product identifier comprises a structured set of attributes; wherein at least one translation rule is a pattern based translation rule; wherein the attributes schema specifies a set of allowable attributes and of allowable values of the attributes.

Abstract: Systems comprising a user interface configured to receive text input by a user and a text prediction engine configured to receive the input text and generate text predictions. The text prediction engine may comprise a general language model and a context-specific language model. The text prediction engine is configured to generate text predictions from the general language model and the context-specific language model and combine the text predictions. The text prediction engine may comprise first and second language models and a first context-specific weighting factor associated with the first language model.

Abstract: According to one embodiment, an input unit accepts input of an input sentence that is a second sentence of the native language corresponding to a first sentence. A language analysis execution unit executes language analysis for the input sentence. A grammatical feature extraction unit extracts a grammatical feature of the input sentence based on a result of the executed language analysis. A search query generation unit generates a search query based on the extracted grammatical feature. An output unit searches for an index based on the generated search query and outputs an exemplary sentence set including an exemplary sentence of the native language corresponding to an index that matches the search query and an exemplary sentence of the foreign language corresponding to the exemplary sentence of the native language.

Abstract: Embodiments are disclosed for transliteration decoding using a tree structure. A method according to some embodiments includes steps of: generating a tree structure for an input string in a first script system, the tree structure including nodes representing segments of the input string; identifying segmentation candidates for the input string based on paths of the tree structure, the segmentation candidates segmenting the input string into character groups; selecting a segmentation candidate based on probabilities of the segmentation candidates predicted by a probabilistic model; segmenting the input string into character groups that correspond to characters in a second script system; decoding the character groups in the first script system into the characters in the second script system, the characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: Computer-assisted multilingual translations may utilize a concept database storing entries for a plurality of concepts, the entries including multilingual vectors of counterpart expressions for the respective concepts in a source language and multiple target languages. In various embodiments, for a given content item having an associated source-language expression, a set of concepts whose database entries match at least the source-language expression is identified, and target-language expressions for the identified concepts are used to iteratively update the set of concepts by identifying therein a subset of concepts that also match a user-selected one of the target-language expressions.

Abstract: Methods, systems, and computer readable medium for providing translated web content. A request is received from a user for content in a second language translated from content in a first language from a first Internet source. The content in the first language is obtained and divided into one or more translatable components. Whether the one or more translatable components have been previously translated, via at least one of machine translation, human translation, and a combination thereof, into the second language and stored as translated components in a storage is determined. If there are one or more translatable components previously translated and stored, the content is generated in the second language by modifying the content in the first language so that at least some translatable components are replaced with corresponding translated components and sent in the second language to the user as a response to the request.

Abstract: A system, method and computer-readable storage devices are for normalizing text for ASR and TTS in a language-neutral way. The system described herein divides Unicode text into meaningful chunks called “atomic tokens.” The atomic tokens strongly correlate to their actual pronunciation, and not to their meaning The system combines the tokenization with a data-driven classification scheme, followed by class-determined actions to convert text to normalized form. The classification labels are based on pronunciation, unlike alternative approaches that typically employ Named Entity-based categories. Thus, this approach is relatively simple to adapt to new languages. Non-experts can easily annotate training data because the tokens are based on pronunciation alone.

Abstract: A parallel-translation dictionary creating apparatus that includes a processor configured to create a parallel-translation dictionary; the processor extracts words from each of the plurality of documents; performs an estimation and storage of a semantic classification of the extracted words; based on a result of the estimation of the semantic classification for the word in the document that is a current processing target and the word pair registered in the parallel-translation word list; updates, to the semantic classification of the word for which the semantic classification has been estimated, the semantic classification of a corresponding word that corresponds to the word and to the subject matter of the document that is the current processing target; and creates the parallel-translation dictionary based on the semantic classification of the word obtained by the estimation of the semantic classification of the word and the update of the semantic classification of the corresponding word.

Abstract: A system and method for out-of-vocabulary compound word handling is provided. Embodiments may include storing a plurality of compound word rules and compound word dictionaries in a database. Embodiments may also include evaluating membership criteria associated with a received compound word, wherein membership criteria includes at least one of dictionary based or part of speech (POS) based criteria. Embodiments may further include applying one or more filtering rules to the received compound word.

Abstract: Various embodiments of systems, computer program products, and methods to provide domain similarity scores for information retrieval are described herein. In an aspect, a plurality of files associated with a plurality of domains are retrieved. A corpus corresponding to the plurality of domains is generated based on the plurality of files by integrating the plurality of files corresponding to the plurality of domains. Further, similarity scores between the plurality of domains are determined based on the generated corpus. The similarity scores between the plurality of domains are persisted in a similarity scores repository to enable information retrieval during translating data between different languages.

Abstract: Various embodiments described herein facilitate multi-lingual communications. The systems and methods of some embodiments enable multi-lingual communications through different modes of communication including, for example, Internet-based chat, e-mail, text-based mobile phone communications, postings to online forums, postings to online social media services, and the like. Certain embodiments implement communication systems and methods that translate text between two or more languages. Users of the systems and methods may be incentivized to submit corrections for inaccurate or erroneous translations, and may receive a reward for these submissions. Systems and methods for assessing the accuracy of translations are described.

Abstract: A remote operation apparatus includes: a display that displays a desktop screen of an apparatus to be remotely operated; and a controller that displays an input field and displays a soft keyboard in a case in which a specific operation is performed on a displayed desktop screen, and enables text input to the input field with the soft keyboard.

Abstract: An information processing system is communicable with a translation server through a network, and includes a receiver, circuitry, and a transmitter. The receiver receives content data indicating contents expressed in a first language and destination information indicating a destination to which the content data is to be transmitted. The circuitry determines, based on the destination information received by the receiver, a second language as a target language into which the contents expressed in the first language is to be translated. The transmitter transmits, to the destination indicated by the destination information, translated content data indicating contents that is translated by the translation server from the first language to the second language.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural machine translation. In one aspect, a system is configured to receive an input sequence of source embeddings representing a source sequence of words in a source natural language and to generate an output sequence of target embeddings representing a target sequence of words that is a translation of the source sequence into a target natural language, the system comprising: a dilated convolutional neural network configured to process the input sequence of source embeddings to generate an encoded representation of the source sequence, and a masked dilated convolutional neural network configured to process the encoded representation of the source sequence to generate the output sequence of target embeddings.

Abstract: Systems and methods of various embodiments may enable or refine translation of text between a first language and a second language. In particular, systems and methods may enable or refine a text translation by soliciting and/or receiving feedback for: translation of a first word or phrase from a first language to a second language; transformation of the first word or phrase (in the first language) to a second word or phrase in the first language; or transformation of the first word or phrase (in the first language) to a second word or phrase in the second language. The systems and methods of various embodiments may incentivize user feedback for failed translations in order to encourage user feedback, improve the quality of user feedback received, and to permit development of translation corpora that can evolve with time.

Abstract: A method for providing a translation, including: acquiring a first sentence in a first language via a user terminal; determining whether the first sentence is in a database including sentences in the first language and corresponding translations in a second language; if the first sentence is not in the database, generating second sentences by replacing one or more words in the first sentence, based on a predetermined rule; calculating respective degrees of coincidence for syntax between the second sentences and sentences in the first language included in the database; extracting third sentences in the first language which are included in the database and for which the calculated degree of coincidence is at least a threshold value; and displaying fourth sentences in the second language which are corresponding translations for the third sentences in the database, on the user terminal as corresponding translation references for the first sentence.

Abstract: A rendering engine and method for a displaying foreign-text string and its translation in a single, composite-text string so as to reduce eye fatigue and thought interruption associated with eye shift between typical display schemes in which the foreign-text string and its translation are each presented in different fields of vision.

Abstract: An automatic speech recognition (ASR) device may be configured to predict pronunciations of textual identifiers (for example, song names, etc.) based on predicting one or more languages of origin of the textual identifier. The one or more languages of origin may be determined based on the textual identifier. The pronunciations may include a hybrid pronunciation including a pronunciation in one language, a pronunciation in a second language and a hybrid pronunciation that combines multiple languages. The pronunciations may be added to a lexicon and matched to the content item (e.g., song) and/or textual identifier. The ASR device may receive a spoken utterance from a user requesting the ASR device to access the content item. The ASR device determines whether the spoken utterance matches one of the pronunciations of the content item in the lexicon. The ASR device then accesses the content when the spoken utterance matches one of the potential textual identifier pronunciations.

Abstract: A terminal equipment comprising: a voice input unit to accept an input of a voice; a speech recognition command unit to command a speech recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice to the voice data of the voice accepted previously into character information of a first language at an interval; a character transmission unit to transmit first character information of the first language toward another terminal equipment whenever receiving the first character information of the first language converted; a translation command unit to command a translation unit to translate second character information of a second language into the first language whenever receiving the second character information of the second language; and a display unit to display the second character information of the first language together with the second character information of the second language.

Abstract: A language communication device in the form of headphones. The headphones have two earpieces, each of the earpieces having a speaker, a first of the earpieces having a short range receiver for receiving audible signals representative of a first language, and a second of the earpieces having a short range transceiver. A microphone input unit is also provided. A control unit connected to the earpieces has a memory device and a translation unit for translating the first language into another language. Software resides in the control unit. A momentary switch is provided for allowing a user to access the software. The language communication device also has a mechanism for receiving a content stream such as music from an external source, which content stream can be muted when the momentary switch is pressed by the user or the short range receiver detects audible signals representative of a language.

Abstract: A method for facilitating the high quality translation of matter by multiple translators, which includes a processor obtaining translated segments from a first group, where each translated segment is a translation of a source text segment, where each source text segment is a portion of a source text, and where for each of the source text segments, at least one translated segment is obtained, and selecting a second group and notifying the second group of an opportunity, where the opportunity comprises the group accessing the translated segments obtained from the first group and the second group providing data regarding the quality of the translated segments. The method also includes obtaining data regarding the quality of the segments from the second group and determining a designated translated segment for each source text segment and generating a final translation.

Abstract: A technique for suggesting patterns to search documents for information of interest includes acquiring a working set of spans for a document set that includes one or more documents. A list of one or more suggested patterns is generated by applying a pattern suggestion algorithm (PSA) to the set of spans for each document in the document set. One or more unique patterns are generated by applying a pattern consolidation algorithm (PCA) to the generated list of suggested patterns. Pattern information for each of the unique patterns is then generated. The pattern information includes a respective first count that corresponds to the number of times each of the unique patterns occurs in the document set.

Abstract: Methods of recognizing motions of an object in a video clip or an image sequence are disclosed. A plurality of frames are selected out of a video clip or an image sequence of interest. A text category is associated with each frame by applying an image classification technique with a trained deep-learning model for a set of categories containing various poses of an object within each frame. A “super-character” is formed by embedding respective text categories of the frames as corresponding ideograms in a 2-D symbol having multiple ideograms contained therein. Particular motion of the object is recognized by obtaining the meaning of the “super-character” with image classification of the 2-D symbol via a trained convolutional neural networks model for various motions of the object derived from specific sequential combinations of text categories. Ideograms may contain imagery data instead of text categories, e.g., detailed images or reduced-size images.

Abstract: A translation support system and the like are provided that is capable of preventing wasteful tasks due to simultaneous operations by more than one person and preventing inconsistent translation of translation words even in a case where a number of persons are simultaneously involved in the translation operations.

Abstract: A method for machine translation, comprising receiving a source string in a source language, an indication of a target language, and user identification information. The method includes using the user identification information to identify at least one memory with user-specific translation data. The method includes tokenizing the source string, using at least one processor, to produce a tokenized source string comprising any unique temporary textual elements associated with corresponding target textual elements during tokenization. The method includes obtaining a translated string from a translator, the translated string being at least a partial translation of the tokenized source string and including all of the unique temporary textual elements. The method includes generating an output string using at least one processor, the generation comprising replacing all of the unique temporary textual elements in the translated string with the associated target textual elements.

Abstract: One embodiment of the present invention sets forth a technique for translating textual content. The technique includes receiving a request to translate an element of source text from an origin language to a target language and searching a database for an element of matching text in the origin language that at least partially matches the element of source text. The technique further includes, if an element of matching text is found in the database, then reading from the database an element of previously translated text that is mapped to the element of matching text and includes at least one word that is translated into the target language, and transmitting the element of source text, the element of matching text, and the element of previously translated text to a location for translation, or if an element of matching text is not found in the database, then transmitting the element of source text to the location for translation.

Abstract: A method for rendering text onto moving image content. The method comprises receiving a request to translate dialog associated with moving image content, transmitting an interface, transmitting a time-stamped transcription, and receiving a translation of the dialog.

Abstract: The present invention relates to the use of a plurality of dependency trees in tree-based statistical machine translation and proposes a dependency forest to effectively process the plurality of dependency trees. The present invention can improve a translation capability by generating a translation rule and a dependency language model by using the dependency forest and applying the generated translation rule and dependency language model when a source language text is converted to a target language text.

Abstract: In one embodiment, a method includes obtaining text from a user, applying the text to a deep learning neural network to generate a plurality of bias coordinates defining a point in an embedded space, and, in response to determining that at least one of the plurality of bias coordinates exceeds a threshold, providing an indication of bias to the user.

Abstract: Proposed are a method and device for constructing an event knowledge. The method comprises: identifying text to obtain an event mining candidate sentence; dividing the event mining candidate sentence into syntax fragments; generating an event knowledge instance according to the syntax fragments and a preset event knowledge construction, in which the number of the event knowledge instances is equal to the number of verb-object fragments and subject-predicate fragments in the syntax fragments; obtaining an event mining target sentence according to the verb-object fragments and the subject-predicate fragments in the syntax fragments, dividing the event mining target sentence, and writing divided members into an event knowledge instance correspondingly, so as to accomplish construction of the event knowledge base.

Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.

Abstract: A system that incorporates the subject disclosure may include, for example, receive user speech captured at a second end user device during a communication session between the second end user device and a first end user device, apply speech recognition to the user speech, identify an unclear word in the user speech based on the speech recognition, adjust the user speech to generate adjusted user speech by replacing all or a portion of the unclear word with replacement audio content, and provide the adjusted user speech to the first end user device during the communication session. Other embodiments are disclosed.

Abstract: Technologies are disclosed herein for statistical machine translation. In particular, the disclosed technologies include extensions to conventional machine translation pipelines: the use of multiple domain-specific and non-domain-specific dynamic language translation models and language models; cluster-based language models; and large-scale discriminative training. Incremental update technologies are also disclosed for use in updating a machine translation system in four areas: word alignment; translation modeling; language modeling; and parameter estimation. A mechanism is also disclosed for training and utilizing a runtime machine translation quality classifier for estimating the quality of machine translations without the benefit of reference translations.

Abstract: A content management system (CMS) and a translation management system (TMS) can utilize content dimensions for content items to manage and translate the content items between languages. Machine and human translations of complex dynamic content can also be improved by pre-rendering the content to remove localization-related syntax prior to machine or human translation. Content items can also be scored as to their suitability for localization prior to translation, and translation can be skipped for content items that do not have a sufficiently high score. Semantic and natural language processing (NLP) techniques can also be utilized for content categorization and routing. Translations of content items can also be continuously refined and higher quality re-translated content can be provided in an automated fashion.

Abstract: An information processing system includes an information processing apparatus, a server, first and second obtaining units, an addition unit, and a second processing unit. The first obtaining unit obtains second information indicating first information held by the server when the information processing apparatus has not previously included the first information to perform second processing necessary for first processing. When receiving a first request for requesting to perform the first processing, the second obtaining unit obtains token information indicating the presence of the authority to use the second information. When the second obtaining unit has obtained the token information, the addition unit adds the token information to a second request for requesting to perform the second processing. Only when the token information has been added to the second request, the second processing unit performs the second processing by using the second information.

Abstract: A social networking system determines whether a particular user is qualified to provide translations of text from a first language to a second language. The determination may include evaluation of the language competencies of the user, and also of the trustworthiness of the user as a translator, as determined based on prior translations submitted by the user. The social networking system also selects translations of a text item for a user to whom that text is to be shown. When evaluating a candidate translation for presentation to the user, the evaluation may assess factors such as the determined qualification as a translator of the user who provided the candidate translation; a quality score of the candidate translation itself; and/or the similarity of the user viewing the content and the user providing the candidate translation.

Abstract: An apparatus and a method for transmitting traffic-related data in road traffic include transmitting the traffic-related data in the form of dynamically generated QR codes from a transmission or display device to a mobile unit hosted by at least one vehicle, and wherein the mobile unit hosted by the vehicle is designed likewise to transmit dynamically generated QR codes. The mobile unit may include an organic light emitting diode (OLED) display, or a smartphone, tablet, or similar device positioned for visibility through a vehicle window.

Abstract: A platform and related components are provided for managing and executing various processes involving distributed, crowd and automated resources, including human and machine language-based translation, are described, including methods and systems for creating and intelligently distributing cognizable translation units among internal workers, outsourcing centers, and crowd workers and methods and systems for on-demand translation.

Abstract: Methods, systems and program product are disclosed for determining matching level of a text lookup segment with a plurality of source texts in a translation memory in terms of context. The invention determines exact matches for the lookup segment in the plurality of source texts, and determines, in the case that at least one exact match is determined, that a respective exact match is an in-context exact match for the lookup segment in the case that a context of the lookup segment matches that of the respective exact match. Degree of context matching required can be predetermined, and results prioritized. The invention also includes methods, systems and program products for storing a translation pair of source text and target text in a translation memory including context, and the translation memory so formed. The invention ensures that content is translated the same as previously translated content and reduces translator intervention.

Abstract: In one embodiment, a translation system may use a translation bug prediction model to more efficiently identify translation errors in a user interface text string. The translation system may apply a translation bug prediction model to a translation resource to identify a potential error source. The translation system may associate an attention flag with the translation resource when identified as the potential error source. The translation system may execute an automatic translation of the translation resource to create a translation target.

Abstract: An encoder and a re-packager circuit. The encoder may be configured to generate one or more bitstreams each having (i) a video portion, (ii) a subtitle placeholder channel, and (iii) a plurality of caption channels. The re-packager circuit may be configured to generate one or more re-packaged bitstreams in response to (i) one of the bitstreams and (ii) a selected one of the plurality of caption channels. The re-packaged bitstream moves the selected caption channel into the subtitle placeholder channel.

Abstract: A content management system (CMS) and a translation management system (TMS) can utilize content dimensions for content items to manage and translate the content items between languages. Machine and human translations of complex dynamic content can also be improved by pre-rendering the content to remove localization-related syntax prior to machine or human translation. Content items can also be scored as to their suitability for localization prior to translation, and translation can be skipped for content items that do not have a sufficiently high score. Semantic and natural language processing (NLP) techniques can also be utilized for content categorization and routing. Translations of content items can also be continuously refined and higher quality re-translated content can be provided in an automated fashion.

Abstract: A method, system, and framework provide the ability to distribute media content. Title information for a media asset is acquired into a computer database. Distribution requirements (e.g., file requirements for files required to distribute the media asset) for retailers and territories are maintained in the database. Desired retailers are selected. Based on the title information and the desired retailers, territories with distribution requirements that match the title information are automatically selected. File requirements for the selected desired retailers and selected territories are displayed. An order is created (the order is based on the title information, the selected desired retailers, the selected territories, and the file requirements). Files identified by the file requirements are received. Based on the order, the received files are automatically submitted (for distribution of the media asset) to the selected retailers.

Abstract: Approaches presented herein enable reduction of characters in a character-limited scenario by minimally editing a text to remain within a character limit while maintaining a tone of a user's writing. More specifically, as a user enters text into a character-limited field, character reduction opportunities for shortening words or phrases are identified in the text. These identified opportunities for shortening words or phrases are compared with a historical writing tone profile of the user in order to preserve a tone and style of the user. Words or phrases that are presented and implemented to shorten the text entered by the user are only sufficient to bring a character count of the entered text within the character limit of the character-limited field. Once the text is within the character limit, no further character reduction is applied.