259 results about "Morpheme" patented technology

A method and apparatus are provided for segmenting words into component parts. Under the invention, mutual information scores for pairs of graphoneme units found in a set of words are determined. Each graphoneme unit includes at least one letter. The graphoneme units of one pair of graphoneme units are combined based on the mutual information score. This forms a new graphoneme unit. Under one aspect of the invention, a syllable n-gram model is trained based on words that have been segmented into syllables using mutual information. The syllable n-gram model is used to segment a phonetic representation of a new word into syllables. Similarly, an inventory of morphemes is formed using mutual information and a morpheme n-gram is trained that can be used to segment a new word into a sequence of morphemes.

The invention concerns a method and corresponding system for building a phonotactic model for domain independent speech recognition. The method may include recognizing phones from a user's input communication using a current phonotactic model, detecting morphemes (acoustic and / or non-acoustic) from the recognized phones, and outputting the detected morphemes for processing. The method also updates the phonotactic model with the detected morphemes and stores the new model in a database for use by the system during the next user interaction. The method may also include making task-type classification decisions based on the detected morphemes from the user's input communication.

A voice recognition method for a single sentence including a multi-instruction in an interactive voice user interface, method includes steps of detecting a connection ending by analyzing the morphemes of a single sentence on which voice recognition has been performed, separating the single sentence into a plurality of passages based on the connection ending, detecting a multi-connection ending by analyzing the connection ending and extracting instructions by specifically analyzing passages including the multi-connection ending and outputting a multi-instruction included in the single sentence by combining the instructions extracted in the step of extracting instructions. In accordance with the present invention, consumer usability can be significantly increased because a multi-operation intention can be checked in one sentence.

Systems and methods are provided for automated semantic role labeling for languages having complex morphology. In one aspect, a method for processing natural language text includes receiving as input a natural language text sentence comprising a sequence of white-space delimited words including inflicted words that are formed of morphemes including a stem and one or more affixes, identifying a target verb as a stem of an inflicted word in the text sentence, grouping morphemes from one or more inflicted words with the same syntactic role into constituents, and predicting a semantic role of a constituent for the target verb.

A method and system for providing a representative phrase corresponding to a real time (current time) popular keyword. The method and system may extend a representative criterion word, determined by analyzing morphemes of words in documents grouped into a cluster, and may combine the extended representative criterion word and the popular keyword, thereby providing the representative phrases. The method and system may display the popular keyword and the representative phrases on a web page, or the like.

An apparatus and method for detecting a named-entity. The apparatus includes a candidate-named-entity extraction module that detects a candidate-named-entity based on an initial learning example and feature information regarding morphemes constituting an inputted sentence, the candidate-named-entity extraction module providing a tagged sentence including the detected candidate-named-entity; a storage module that stores information regarding a named-entity dictionary and a rule; and a learning-example-regeneration module for finally determining whether the candidate-named-entity included in the provided sentence is a valid named-entity, based on the named-entity dictionary and the rule, the learning-example-regeneration module providing the sentence as a learning example, based on a determination result, so that a probability of candidate-named-entity detection is gradually updated.

An audio-based data indexing and retrieval system for processing audio-based data associated with a particular language, comprising: (i) memory for storing the audio-based data; (ii) a semantic unit based speech recognition system for generating a textual representation of the audio-based data, the textual representation being in the form of one or more semantic units corresponding to the audio-based data; (iii) an indexing and storage module, operatively coupled to the semantic unit based speech recognition system and the memory, for indexing the one or more semantic units and storing the one or more indexed semantic units; and (iv) a search engine, operatively coupled to the indexing and storage module and the memory, for searching the one or more indexed semantic units for a match with one or more semantic units associated with a user query, and for retrieving the stored audio based data based on the one or more indexed semantic units. The semantic unit may preferably be a syllable or morpheme. Further, the invention is particularly well suited for use with Asian and Slavic languages.

A method and system for retrieving information from a set of documents using one retrieval keyword or more is capable of remarkably increasing the relevance ratio of a retrieval result. The system includes a category dictionary for storing category information containing morphemes included in the documents in a hierarchical structure, a morpheme-ID array produced by converting the set of documents into a set of fixed-length IDs in accordance with the morphemes while maintaining order information of the morphemes, and a retrieval part for retrieving a morpheme ID from the morpheme-ID array. The retrieval part retrieves a morpheme ID of the retrieval word and of any morpheme co-occurring with the retrieval word and having category information which matches retrieval-category information.

When it accepts an input sentence, the present apparatus divides the input sentence into substrings through morpheme analysis and obtains a candidate word group for translation of the substrings from a machine translation dictionary. It then obtains information on occurrence of each candidate word in the candidate word group within a bilingual example sentence database and calculates their priorities based on the occurrence information. Then, it grants priority as translation to each of the candidate words to generate a prioritized candidate word group and sorts the candidate words in descending order of priority for output.

The present disclosure generally relates to systems and processes for morpheme-based word prediction. An example method includes receiving a current word; determining a context of the current word based on the current word and a context of a previous word; determining, using a morpheme-based language model, a likelihood of a prefix based on the context of the current word; determining, using the morpheme-based language model, a likelihood of a stem based on the context of the current word; determining, using the morpheme-based language model, a likelihood of a suffix based on the context of the current word; determining a next word based on the likelihood of the prefix, the likelihood of the stem, and the likelihood of the suffix; and providing an output including the next word.

A method of syntax analysis based on a mobile configuration concept, and a natural language search method using the syntax analysis method, are provided. The syntax analysis method includes morpheme analysis and syntax analysis after establishing a morpheme dictionary program for analyzing morphemes of an input sentence, and a subcategorization database storing the details of subcategories belonging to heads, such as stems of words and word endings, of each component of a sentence such that the syntactic status of an inflective word ending is admitted based on the marker theory which regards both postpositions and endings as syntactic units, and combination relations between words can be grammatically defined as a whole. In the morpheme analysis, if a sentence desired to be analyzed is input, the contents of morphemes are analyzed in units of polymorphemes according to the morpheme dictionary program, and after selecting an analysis case of a morpheme appropriate to the input data among morpheme analysis data by polymorpheme, preprocessing is performed. In the syntax analysis, with the analyzed morphemes, partial structures of a sentence are first established according to grammatical roles stored in a grammar rule database, and then, by using the subcategorization database, the entire structure is established. Then, by calculating the weighted value of each structure, a most appropriate optimum case is determined and output. Accordingly, any scrambled sentence can be easily and quickly analyzed without any sophisticated parsing apparatus. Also, the grammatical relationships between expressions forming a sentence can be accurately captured such that information requested by a user is retrieved in the same manner as a human-being makes a decision, and accurate information can be provided.

A user-interactive automatic translation device for a mobile device, includes: a camera image controller for converting an image captured by a camera into a digital image; an image character recognition controller for user-interactively selecting a character string region to be translated from the digital image, performing a character recognition function on the selected character string region based on an optical character reader (OCR) function and character recognition information to generate a text string; and user-interactively correcting errors included in the text string. Further, the user-interactive automatic translation device includes a text transmission controller for transmitting the error-corrected text string; and an automatic translation controller for receiving the error-corrected text string from the text transmission controller, performing a morpheme analysis, tagging, a structure analysis, a structure conversion, and a vocabulary conversion on the text string to generate a translation of the text string based on a grammar of a target language.

Given a source text, a desired translation of the source text into a target language, and a machine-readable dictionary, a first set of morphemes in the target language is generated from the source text, typically by using the dictionary to perform a machine translation of the source text. The second text is analyzed into a second set of morphemes in the target language. Differences between the first and second sets of morphemes are found, and morphemes corresponding to the differences are taken from the source text. Existing information including these source-text morphemes is extracted from the dictionary, and new information to be added to the dictionary is automatically generated from the extracted information and the differences. This process generates comparatively short dictionary entries, corresponding only to the differences between the two set of morphemes, and therefore creates useful dictionary entries while saving dictionary space.

Disclosed are a hybrid automatic translation method and apparatus employing a combination of a rule-based method and a translation pattern method, and a computer readable medium thereof, which is capable of solving an ambiguity problem of the conventional rule-based method and a pattern generation and coverage problem of the translation pattern method. The hybrid automatic translation apparatus includes: a morpheme analyzing block for analyzing a morpheme of an inputted source sentence and determining parts of speech; a syntactic structure analyzing block for parsing the tagging result to output a parsing tree; a construction pattern generating block for extracting only a chunking result of phrases belonging to sub-category from the parsing tree to generate a construction pattern; a construction pattern translating block for translating the construction pattern by using a translation pattern; a clause structure analyzing block for analyzing a clause unit structure of the if the translation pattern matching of the construction pattern fails; and a partial pattern translating block for performing a pattern translation of partial construction pattern according to the result of the clause structure analysis to output a final translation result.

The present invention includes a morpheme extracting unit 420 configured to extract, based on a character string corresponding to input information, at least one morpheme constituting a minimum unit of the character string, as first morpheme information, a topic search unit 340 configured to compare the first morpheme information extracted at the morpheme extracting unit 420 with topic titles, and to search a topic title corresponding to the first morpheme information from among the topic titles, and a reply retrieval unit 350 configured to retrieve, based on the topic title searched at a topic identification information search unit 320, a reply sentence associated with the topic title.

A device for analyzing reputation for objects by data mining is provided. The device includes a big data collector assembly collecting first information from a web page, a text preprocessor assembly analyzing morpheme information from an original text of the first information, an ontology dictionary extender assembly classifying the morpheme information according to each category and extracting an associated word, an object recognizer assembly measuring similarity between the associated word from the morpheme information to recognize a plurality of entity names associated with a first object, an information sensitivity classifier assembly classifying sensitivity of the first information based on a frequency of a sensitive word associated with the first object from the morpheme information, and a risk evaluation modeler assembly deriving a numeric risk value of the first information according to a numeric sensitivity value of the sensitive word and a weight value level for evaluating event importance.

To enable a user to perform, by using an ontology, an information search utilizing a meaning given to information on a network by Semantic Web without being required to perform complicated operations for forming an inquiry sentence in conformity with the ontology. In a stage before a search engine for performing an information search by using an ontology is provided an information search supporting system having a morpheme analysis section, a syntactic and semantic analysis section, and a conversion execution section which converts a natural language sentence on which syntactic analysis and semantic analysis have been performed into an inquiry sentence described in an ontology description language by referring to a case frame ontology dictionary in which are stored information indicating to which property in an ontology does the relationship among a predicate, a subject and an object in the natural language sentence correspond and the case frame of the natural language sentence in the property. A natural language sentence is input and an inquiry sentence described in the ontology language is formed on the basis of the results of syntactic analysis and semantic analysis on the natural language sentence and is provided to the search engine.

The invention concerns a method and system for detecting morphemes in a user's communication. The method may include recognizing a lattice of phone strings from the user's input communication, the lattice representing a distribution over the phone strings, and detecting morphemes in the user's input communication using the lattice. The morphemes may be acoustic and / or non-acoustic. The morphemes may represent any unit or sub-unit of communication including phones, diphones, phone-phrases, syllables, grammars, words, gestures, tablet strokes, body movements, mouse clicks, etc. The training speech may be verbal, non-verbal, a combination of verbal and non-verbal, or multimodal.

The invention provides a chat robot system and an automatic chat method; the chat robot system comprises an interactive platform, a word segmenting module, a language recognition unit, a database and an information search unit, wherein the word segmenting module is connected with the interactive platform and used for segmenting the speech sent by a user; the speech recognition unit is connected with the word segmenting module and used for judging the morpheme of each segmented word and judging the type of a sentence stated by the user; the database further comprises an event base, an action base, a knowledge base and a thought base which are respectively used for storing event information, action information, knowledge information and thought information simulating the human brain; and the information search unit is respectively connected with the language recognition unit, the database and the interactive platform and used for searching the database according to the morpheme of the segmented word and the sentence type, and transmitting the search result to the interactive platform. The chat robot system has the advantages of high accuracy, low cost and strong expandability.

A statistical machine translation apparatus and method reflecting linguistic information are provided. In the process of generating a translation model based on statistical information on source language sentences and target language sentences during word alignment, the translation model is generated using word alignment results that are amended based on a bilingual dictionary. Further, instead of using the source language sentence and the target language sentence (i.e., their bilingual corpora) as materials to generate the translation model, it is determined whether or not the morphemes are meaningful content words in the source and target language sentences. Based on the determination, pre-processing is performed on the source language sentence and the target language sentence.

A searching method of network includes using multi-element composite morpheme with multiple morpheme as indexing word to set up file-indexing, dividing index key word inputted by user to be a multi-element composite morpheme and carrying out network search according to divided multi-element composite morpheme.

Provided are a device and method for interactive machine translation. The device includes a machine translation engine having a morphological / syntactic analyzer for analyzing morphemes and sentences of an original text and generating original text analysis information, and a translation generator for generating a translation and translation generation information on the basis of the original text analysis information, and a user interface module for displaying sentence structures of the original text and the translation, and a relationship between the original text and the translation to a user on the basis of the original text analysis information and the translation generation information, and for receiving corrections to the original text or the translation from the user. The device and method provide a user interface whereby the user can effectively recognize and correct a mistranslated part and a cause of the mistranslation, and rapidly provides a re-translated result according to the correction. Thus, it is possible to perform high-quality translation which satisfies the user.

A Chinese word segmentation method based on navigation information retrieval is characterized in that a word segmentation system is obtained through the steps that a dictionary is loaded, and text code conversion is carried out; segmentation processing is carried out, and a source character string is segmented into a plurality of slightly simpler short sentences; atomic word segmentation is carried out to obtain the smallest morpheme units which cannot be segmented in the short sentences; word forming full-match is achieved with a word-by-word traversal matching method; the matching results are screened to generate a plurality of best results; human names, place names and proper nouns are processed; the dictionary is corrected, and mainly, unlisted new words are added, and properties of the existing words are improved; the processing results of all the short sentences are finally combined to be output. The Chinese word segmentation method has the advantages that content input by a user can be formed into words through the Chinese word segmentation technology, the speed can be optimized, wrongly written characters can be corrected with the words as the basis, and a more suitable result can be provided. With the Chinese word segmentation technology, semantics can be understood by an information retrieval engine better, and the provided result set can be fully adjusted.

A machine translating apparatus includes an input unit that inputs a source language sentence, a syntax analyzing unit that performs a syntactic analysis on the source language sentence and generates syntax information, an extracting unit that extracts from the syntax information the first partial information that includes the first partial structure including all the nodes under the most significant nodes that are the nodes of the syntax information and the corresponding morphemes, and also extracts the second partial information including the second subtree representing a difference between two items of the first partial information and the corresponding morphemes, a translating unit that translates the morphemes of all the items of the partial information with multiple translation systems, and a most-plausible structure selecting unit that selects a combination for which the average of the translation scores takes the maximum value.

The present invention provides a Korean-English hybrid automatic translation method for providing translation from Korean to English, includes: performing a morpheme analysis and a syntactic analysis on a Korean input source text; segmenting the Korean input source text into at least two source text segments, based on the results of the morpheme analysis and the syntactic analysis; and generating a PBMT (pattern-based machine translation) translated text segment and a SMT (statistical machine translation) translated text segment with respect to each of the source text segments. Further, the method includes determining, as final translation result, one of the PBMT translated text segment and the SMT translated text segment with respect to each source text segment, based on predetermined weight information; and composing the translated text segments with respect to the source text segments of the Korean input source text into one English translated text by using the determined final translation results.

An analyzing unit performs a morphological analysis of an input character string that is obtained by processing input speech. A generating unit divides the input character string in units of division previously decided, that is composed of one or plural morphemes, and generates partial character strings including part of components of the divided input character string. A candidate output unit outputs the generated partial character strings to a display unit. A selection receiving unit receives a partial character string selected from the outputted partial character strings as a target to be processed.