1038 results about "Machine translation" patented technology

Disclosed is a semantic user interface system that allows text information to be tagged with machine-readable IDs that are associated with concepts for conveying information without any ambiguity or without being hampered by the limitations of human languages. Typically, a plurality of vocabularies are stored across a network, and each vocabulary includes a plurality of machine-readable IDs each corresponding to a concept and at least one keyword corresponding to each machine-readable ID. An input interface accepts text information, selects those machine-readable IDs whose keywords match up with the text information, and returns a list of candidates each corresponding to one of the selected machine-readable IDs and including a corresponding description. The machine-readable IDs can carry information in the form of concepts without any ambiguity as opposed to text information. This system can be applied to web and database searches, publishing messages to selected subscribers, interfacing of applications software, machine translations, etc.

A machine translation method includes receiving a source text string and identifying any named entities. The identified named entities may be processed to exclude common nouns and function words. Features are extracted from the source text string relating to the identified named entities. Based on the extracted features, a protocol is selected for translating the source text string. A first translation protocol includes forming a reduced source string from the source text string in which the named entity is replaced by a placeholder, translating the reduced source string by machine translation to generate a translated reduced target string, while processing the named entity separately to be incorporated into the translated reduced target string. A second translation protocol includes translating the source text string by machine translation, without replacing the named entity with the placeholder. The target text string produced by the selected protocol is output.

A first recognizing unit recognizes a first-language speech as a first-language character string, and outputs a first recognition result. A second recognizing unit recognizes the first-language speech as a most probable first-language example from among first-language examples stored in an example storing unit, and outputs a second recognition result. A retrieving unit retrieves, when a similarity between the first recognition result and the second recognition result exceeds a predetermined threshold, a second-language example corresponding to the second recognition result from the example storing unit.

A system and a method for phrase-based translation are disclosed. The method includes receiving source language text to be translated into target language text. One or more dynamic bi-phrases are generated, based on the source text and the application of one or more rules, which may be based on user descriptions. A dynamic feature value is associated with each of the dynamic bi-phrases. For a sentence of the source text, static bi-phrases are retrieved from a bi-phrase table, each of the static bi-phrases being associated with one or more values of static features. Any of the dynamic bi-phrases which each cover at least one word of the source text are also retrieved, which together form a set of active bi-phrases. Translation hypotheses are generated using active bi-phrases from the set and scored with a translation scoring model which takes into account the static and dynamic feature values of the bi-phrases used in the respective hypothesis. A translation, based on the hypothesis scores, is then output.

An authoring method includes generating an authoring interface configured for assisting a user to author a text string in a source language for translation to a target string in a target language. Initial source text entered by the user is received through the authoring interface. Source phrases are selected that each include at least one token of the initial source text as a prefix and at least one other token as a suffix. The source phrase selection is based on a translatability score and optionally on fluency and semantic relatedness scores. A set of candidate phrases is proposed for display on the authoring interface, each of the candidate phases being the suffix of a respective one of the selected source phrases. The user may select one of the candidate phrases, which is appended to the source text following its corresponding prefix, or may enter alternative text. The process may be repeated until the user is satisfied with the source text and the SMT model can then be used for its translation.

Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.

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.

A method of improving the accuracy of the translation output of Statistical Machine Translation (SMT), while increasing the effectiveness of an ongoing professional human translation effort by correlating the ongoing professional human translation effort directly with the translation errors made by the system. Once the translation errors have been corrected by professional human translators and are re-input to the system, the SMT's training process may ensure that the same, and possibly similar, translation error(s) may not occur again.

In one embodiment, the invention provides a method for machine translation of a source document in an input language to a target document in an output language, comprising generating translation options corresponding to at least portions of each sentence in the input language; and selecting a translation option for the sentence based on statistics associated with the translation options.

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.

A method and a system for making merging decisions for a translation are disclosed which are suited to use where the target language is a productive compounding one. The method includes outputting decisions on merging of pairs of words in a translated text string with a merging system. The merging system can include a set of stored heuristics and / or a merging model. In the case of heuristics, these can include a heuristic by which two consecutive words in the string are considered for merging if the first word of the two consecutive words is recognized as a compound modifier and their observed frequency f1 as a closed compound word is larger than an observed frequency f2 of the two consecutive words as a bigram. In the case of a merging model, it can be one that is trained on features associated with pairs of consecutive tokens of text strings in a training set and predetermined merging decisions for the pairs. A translation in the target language is output, based on the merging decisions for the translated text string.

A language recognition system, method and program product for recognizing language based input from computer users on a network of connected computers. Each computer includes at least one user based language model trained for a corresponding user for automatic speech recognition, handwriting recognition, machine translation, gesture recognition or other similar actions that require interpretation of user activities. Network computer users are clustered into classes of similar users according to user similarities such as, nationality, profession, sex, age, etc. User characteristics are collected by sensors and from databases and, then, distributed over the network during user activities. Language models with similarities among similar users on the network are identified. The language models include a language model domain, with similar language models being clustered according to their domains. Language models identified as similar are modified in response to user production activities. After modification of one language model, other identified similar language models are compared and adapted. Also, user data, including information about user activities and language model data, is transmitted over the network to other similar users. Language models are adapted only in response to similar user activities, when these activities are recorded and transmitted over the network. Language models are given a global context based on similar users that are connected together over the network.

A system and method for hybrid machine translation approach is based on a statistical transfer approach using statistical and linguistic features. The system and method may be used to translate from one language into another. The system may include at least one database, a rule based translation module, a statistical translation module and a hybrid machine translation engine. The database(s) store source and target text and rule based language models and statistical language models. The rule based translation module translates source text based on the rule based language models. The statistical translation module translates source text based on the statistical language models. A hybrid machine translation engine, having a maximum entropy algorithm, is coupled to the rule based translation module and the statistical translation module and is capable of translating source text into target text based on the rule based and statistical language models.

A method is disclosed for detecting topical changes and topic identification in texts in real time using likelihood ratio based methods. In accordance with the method, topic identification is achieved by evaluating text probabilities under each topic, and then selecting a new topic when one of those probabilities becomes significantly larger than the others. The method is usable to improve real time machine translation.

A machine translation method for translating source text from a first language to target text in a second language includes receiving the source text in the first language and accessing a library of bi-fragments, each of the bi-fragments including a text fragment from the first language and a text fragment from the second language, at least some of the bi-fragments comprising non-contiguous bi-fragments in which at least one of the text fragment from the first language and the text fragment from the second language comprises a non-contiguous fragment.

A method of utilizing multiple Machine Translation “Language Pairs” to create a “Community of Language Pairs” (The Community) that consists of one “Language Pair” for every possible combination of every two languages and / or language dialects included in The Community. The present invention greatly enhances the utility of the art of Machine Translation. Utilizing the present invention, any user whose native language, or other language in which the user is fluent, which is included in The Community may now have access to machine translations of electronically recorded material produced in any other language, or language dialect, included in The Community. The present invention applies to both machine translation of material that is electronically recorded in different languages included in The Community, as well as real time interactive communication with and among multiple users whose native language, or other language in which each user is fluent, is included in The Community.

A method and computer system for analyzing sentences of various languages and constructing a language-independent semantic structure are provided. On the basis of comprehensive knowledge about languages and semantics, exhaustive linguistic descriptions are created, and lexical, morphological, syntactic, and semantic analyses for one or more sentences of a natural or artificial language are performed. A computer system is also provided to implement, analyze and store various linguistic structures and to perform lexical, morphological, syntactic, and semantic analyses. As result, a generalized data structure, such as a semantic structure, is generated and used to describe the meaning of one or more sentences in language-independent form, applicable to automated abstracting, machine translation, control systems, Internet information retrieval, etc.

A method and apparatus for automating the acquisition, reconstruction, and generation of knowledgebases of associated ideas and using such knowledgebases in many applications including machine translation of human languages, search and retrieval of unstructured text, or other data, based on concept search, voice recognition, data compression, and artificial intelligence systems.

A quality-prediction engine predicts a trust level associated with translational accuracy of a machine-generated translation. Training a quality-prediction may include translating a document in a source language to a target language by executing a machine-translation engine stored in memory to obtain a machine-generated translation. The training may further include comparing the machine-generated translation with a human-generated translation of the document. The human-generated translation is in the target language. Additionally, the training may include generating a mapping between features of the machine-generated translation and features of the human-generated translation based on the comparison. The mapping may allow determination of trust levels associated with translational accuracy of future machine-generated translations that lack corresponding human-generated translations. Machine-generated translations may then be credibly provided by translating a document from a source language to a target language by executing a machine-translation engine stored in memory to obtain a machine-generated translation, predicting a trust level of the machine-generated translation by executing a quality-prediction engine stored in memory, and outputting the machine-generated translation and the trust level.

A translating apparatus includes a speech recognition unit, a machine translation unit, a speech synthesizing unit, and a dialog management unit. The speech recognition unit recognizes input speech, and supplies the result of the speech recognition to the machine translation unit. The machine translation unit translates the result of the speech recognition. When a Japanese-speaking user and an English-speaking user speak to each other, the dialog management unit stores a history of dialogs, and determines based on the dialog history and prestored knowledge whether the result of the translation by the machine translation unit is unnatural compared with the flow of the dialog. When the result of the translation is unnatural, the dialog management unit outputs, to the machine translation unit, information representing the unnatural result. This controls the machine translation unit to perform translation again.

The disclosed system translates into different languages HTML documents available through the World Wide Web. HTML documents are translated by machine translation software bundled in a browser. Alternatively, documents are retrieved as needed, translated, and stored on a Web server so user requests are serviced with a document that has been translated from a different language. The disclosed invention expands usage of the Internet for non-English speakers.

A method and apparatus for stochastic finite-state machine translation is provided. The method may include receiving a speech input and translating the speech input in a source language into one or more symbols in a target language based on stochastic language model. Subsequently, all possible sequences of the translated symbols may be generated. One of the generated sequences may be selected based on a monolingual target language model.

A translation method and system include a recognition engine having a plurality of models each being employed to decode a same utterance to provide an output. A model combiner is configured to assign probabilities to each model output and configured to assign weights to the outputs of the plurality of models based on the probabilities to provide a best performing model for the context of the utterance.

A machine translation method and system for improving the accuracy of the selection of appropriate words, without incurring any deterioration of the processing efficiency, includes registering, during the translation of a document by using a compound word dictionary, elemental word information of an applied compound word in a discourse dictionary, and employing a plurality of dictionaries, including the discourse dictionary, to translate the document without using a compound word dictionary.

A method and system for creating hypercomplex representations of data includes, in one exemplary embodiment, at least one set of training data with associated labels or desired response values, transforming the data and labels into hypercomplex values, methods for defining hypercomplex graphs of functions, training algorithms to minimize the cost of an error function over the parameters in the graph, and methods for reading hierarchical data representations from the resulting graph. Another exemplary embodiment learns hierarchical representations from unlabeled data. The method and system, in another exemplary embodiment, may be employed for biometric identity verification by combining multimodal data collected using many sensors, including, data, for example, such as anatomical characteristics, behavioral characteristics, demographic indicators, artificial characteristics. In other exemplary embodiments, the system and method may learn hypercomplex function approximations in one environment and transfer the learning to other target environments. Other exemplary applications of the hypercomplex deep learning framework include: image segmentation; image quality evaluation; image steganalysis; face recognition; event embedding in natural language processing; machine translation between languages; object recognition; medical applications such as breast cancer mass classification; multispectral imaging; audio processing; color image filtering; and clothing identification.

This invention discloses one machine translation device, which comprises the following parts: sound information input unit to input first sound information; sound identification unit to identify first sound information and to convert it into text information; translation unit to translate text information into second one. This invention translation method comprises the following steps: sound information input unit to input first sound information; sound identification unit to identify first sound information and to convert it into text information; translation unit to translate text information into second one.

Named entity recognition is described, for example, to detect an instance of a named entity in a web page and classify the named entity as being an organization or other predefined class. In various examples, named entity recognition results are used to augment text from which the named entity was recognized; the augmentation may comprise information retrieval results about the named entity mention. In various embodiments, labeled training sentences in many different languages and for many different classes, are obtained to train machine learning components of a multi-lingual, multi-class, named entity recognition system. In examples, labeled training sentences are obtained from at least two sources, a first source using a multi-lingual or monolingual corpus of inter-linked documents and a second source using machine translation training data. In examples, labeled training sentences from the two sources are selectively sampled for training the named entity recognition system.

Provided are two types of translation engines. One of the translation engines translates a text written in a source language X into an intermediate language C, and the other translates the intermediate language C into a target language Y. The X-C translation engine translates an original text written in the source language X into a text in a predetermined intermediate language C as well as acquires and adds annotations obtained by this translation to the translated text written in the intermediate language C. The C-Y translation engine references annotations, which are obtained by the X-C translation engine and added to the text in the intermediate language C, and translates the text in the intermediate language into a text in the target language Y sentence.

A machine translation method includes receiving source text in a first language and retrieving text fragments in a target language from a library of bi-fragments to generate a target hypothesis. Each bi-fragment includes a text fragment from the first language and a corresponding text fragment from the second language. Some of the bi-fragments are modeled as elastic bi-fragments where a gap between words is able to assume a variable size corresponding to a number of other words to occupy the gap. The target hypothesis is evaluated with a translation scoring function which scores the target hypothesis according to a plurality of feature functions, at least one of the feature functions comprising a gap size scoring feature which favors hypotheses with statistically more probable gap sizes over hypotheses with statically less probable gap sizes.