Abstract: A system and method for hybrid processing in a natural language voice services environment that includes a plurality of multi-modal devices may be provided. In particular, the hybrid processing may generally include the plurality of multi-modal devices cooperatively interpreting and processing one or more natural language utterances included in one or more multi-modal requests. For example, a virtual router may receive various messages that include encoded audio corresponding to a natural language utterance contained in a multi-modal interaction provided to one or more of the devices. The virtual router may then analyze the encoded audio to select a cleanest sample of the natural language utterance and communicate with one or more other devices in the environment to determine an intent of the multi-modal interaction. The virtual router may then coordinate resolving the multi-modal interaction based on the intent of the multi-modal interaction.

Abstract: Systems and method are disclosed for dynamically creating a translated virtual website based on a machine translation of an existing website without adding any code to the source website. In one exemplary embodiment, an extension to a URL is recognized as requesting a translated website, and the request is routed to an MT server. The original-language content is retrieved, translated, and returned to the user system without any further action by the user. In a further exemplary embodiment, a secure connection can be established to enable translation of non-public websites. In a further exemplary embodiment, a crawler can index the translated website. In a further exemplary embodiment, an RSS feed returns translated content.

Abstract: A natural language processing system is disclosed herein. Embodiments of the NLP system perform hand-written rule-based operations that do not rely on a trained corpus. Rules can be added or modified at any time to improve accuracy of the system, and to allow the same system to operate on unstructured plain text from many disparate contexts (e.g. articles as well as twitter contexts as well as medical articles) without harming accuracy for any one context. Embodiments also include a language decoder (LD) that generates information which is stored in a three-level framework (word, clause, phrase). The LD output is easily leveraged by various software applications to analyze large quantities of text from any source in a more sophisticated and flexible manner than previously possible. A query language (LDQL) for information extraction from NLP parsers' output is disclosed, with emphasis on its embodiment implemented for LD.

Abstract: A system and method are described for generating semantically similar sentences for a statistical language model. A semantic class generator determines for each word in an input utterance a set of corresponding semantically similar words. A sentence generator computes a set of candidate sentences each containing at most one member from each set of semantically similar words. A sentence verifier grammatically tests each candidate sentence to determine a set of grammatically correct sentences semantically similar to the input utterance. Also note that the generated semantically similar sentences are not restricted to be selected from an existing sentence database.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for learning latent representations for natural language tasks. A system configured to practice the method analyzes, for a first natural language processing task, a first natural language corpus to generate a latent representation for words in the first corpus. Then the system analyzes, for a second natural language processing task, a second natural language corpus having a target word, and predicts a label for the target word based on the latent representation. In one variation, the target word is one or more word such as a rare word and/or a word not encountered in the first natural language corpus. The system can optionally assigning the label to the target word. The system can operate according to a connectionist model that includes a learnable linear mapping that maps each word in the first corpus to a low dimensional latent space.

Abstract: An information processing apparatus includes a category classifying unit configured to classify a document into one or more categories, a word extracting unit configured to extract one or more words from the document, a word score calculating unit configured to calculate a word score for each of the one or more words extracted from the document on the basis of an appearance frequency of the word in each of the one or more categories, the word score serving as an index of interest of the word, a sentence-for-computation extracting unit configured to extract one or more sentences from the document, and a sentence score calculating unit configured to calculate a sentence score for each of the extracted one or more sentences on the basis of the word score calculated by the word score calculating unit, the sentence score serving as an index of interest of the sentence.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space.

Abstract: A method and device for selecting a word to be defined in a mobile communication terminal having an electronic dictionary function. The method includes selecting a word in a displayed text document in response to a first input, displaying the selected word in a search window, searching for the displayed word in response to a request to search for the displayed word, displaying information resulting from the search, and terminating display of the information and displaying the text document.

Abstract: A method provides a non-optimized list of elements, with some of the elements having multiple terms. A table of sub-elements is generated from the elements list, with each sub-element having one term only and with a number of times a sub-element appears in the elements list being weighted in the sub-elements table. A weighted singleton histogram table is generated using a singleton dictionary, and a total popularity score of each singleton is computed from the sub-elements table. For each element from the elements list, an elements score is generated based on the total popularity score of each singleton within the element. An optimally sorted list of the elements list is generated based on the elements scores.

Abstract: A system facilitates cross-language communication among users of respective wireless communication devices. Two or more mutually-agreeing users establish and participate in a cross-language communication session, without revealing private information, such as their telephone numbers. Once the session has been established, each user enters text into her wireless communication device, and a translated version of the entered text is displayed on a screen of the other user's wireless communication device. The text may be entered, such as by typing on a keyboard on the wireless communication device or by speaking inputs into a microphone and automatically recognizing the speech. Optionally, the translated text may be spoken by a speech synthesizer.

Abstract: A translation method is adapted to a domain of interest. The method includes receiving a source text string comprising a sequence of source words in a source language and generating a set of candidate translations of the source text string, each candidate translation comprising a sequence of target words in a target language. An optimal translation is identified from the set of candidate translations as a function of at least one domain-adapted feature computed based on bilingual probabilities and monolingual probabilities. Each bilingual probability is for a source text fragment and a target text fragment of the source text string and candidate translation respectively. The bilingual probabilities are estimated on an out-of-domain parallel corpus that includes source and target strings. The monolingual probabilities for text fragments of one of the source text string and candidate translation are estimated on an in-domain monolingual corpus.

Abstract: A system and method for receiving character input from a user includes a programmed processor that receives inputs from the user and disambiguates the inputs to present character sequence choices corresponding to the input characters. In one embodiment, a first character input is received and a corresponding first recognized character is stored in a temporary storage buffer and displayed to the user for editing. After a predetermined number of subsequent input characters and/or predetermined amount of time without being edited, the system determines that the first recognized character is the intended character input by the user and removes the first recognized character from the buffer, thereby inhibiting future editing.

Abstract: Embodiments of the present invention provide an approach for automatically assigning a confidence level to information extracted from a transcription of a voice recording. Specifically, in a typical embodiment, an axiom is extracted from a source associated with the text of the transcription. A confidence level of the source is determined. A confidence level is assigned to the axiom based on the confidence level of the source.

Abstract: Techniques and solutions are provided for adaptive input language switching. Automatic switching of a current input language can be performed by receiving an indication of a first language of displayed content (where the current input language is set to a second language different from the first language), receiving a selection of a text input area, and based on the selection, automatically switching the current input language from the second language to the first language. Switching of the current input language can also be performed by providing convenient user interface elements for selection by a user to automatically switch the current input language.

Abstract: A method and an apparatus for generating a journal, which can implement automatic generation of a journal based on data from various sources. The method includes: obtaining a source data set and a journal description data set corresponding to the source data set; calculating an alignment probability between each source data sequence and each journal description data sequence to obtain an alignment probability set; calculating a probability that each journal description data sequence occurs in the journal description data set to obtain an occurrence probability set; determining, according to the alignment probability set and the occurrence probability set and from each journal description data sequence, a target journal description data sequence corresponding to a source data sequence to be translated, and translating the target journal description data sequence into a journal description text.

Abstract: A system and method for automatically generating patient-specific and grammatically correct electronic medical records is disclosed. The system and method of an example embodiment includes retrieving a statement from a data object, the data object including the statement, at least one response option corresponding to the statement, and at least one sentence fragment corresponding to the response option; generating, using a processor, a user interface view that includes the statement; receiving a response corresponding to the statement; correlating the response to the at least one response option; retrieving the sentence fragment that corresponds to the correlated response option; and generating, using the processor, a patient-specific and grammatically correct electronic medical record using the retrieved sentence fragment.

Abstract: Systems and methods for searching and browsing a data store of contextually related data objects. The system includes a search/browse module that receives a search query. The search/browse module identifies data objects that match the search query and generates sentences from data objects that are contextually related to the matching data objects. The sentences are human-readable sentences, for example in subject-verb-object format, where each sentence represents the relationship between two data objects. The sentences are output for display as a hierarchy of sentences. Additionally, a user can browse the data store of contextually related data objects by selecting a sentence that is displayed to the user. The search/browse module then outputs attributes of the data object represented by the sentence for display in two separate regions of a user interface.

Abstract: A text processing apparatus is provided with a segment determination unit 36 and a descriptive content determination unit 33. The segment determination unit 36 determines, with respect to a homogeneous segment that is similar to segments constituting a first text which is set as an analysis target (analysis target text) and that is included in another first text, whether the content thereof is included in a second text. The descriptive content determination unit 33 determines whether each segment constituting the analysis target text should be described in a corresponding second text, based on the determination result.

Abstract: Potential linguistic errors within a sequence of words of a sentence are identified based on analysis of a configurable sliding window. The analysis is performed based on an assumption that if a sequence of words occurs frequently enough within a large, well-formed corpus, its joint probability for occurring in a sentence is very likely to be greater than the same words randomly ordered.

Abstract: A clausifier and method of extracting clauses for spoken language understanding are disclosed. The method relates to generating a set of clauses from speech utterance text and comprises inserting at least one boundary tag in speech utterance text related to sentence boundaries, inserting at least one edit tag indicating a portion of the speech utterance text to remove, and inserting at least one conjunction tag within the speech utterance text. The result is a set of clauses that may be identified within the speech utterance text according to the inserted at least one boundary tag, at least one edit tag and at least one conjunction tag. The disclosed clausifier comprises a sentence boundary classifier, an edit detector classifier, and a conjunction detector classifier. The clausifier may comprise a single classifier or a plurality of classifiers to perform the steps of identifying sentence boundaries, editing text, and identifying conjunctions within the text.