1428 results about "Part of speech" patented technology

An ontology-based parser incorporates both a system and method for converting natural-language text into predicate-argument format that can be easily used by a variety of applications, including search engines, summarization applications, categorization applications, and word processors. The ontology-based parser contains functional components for receiving documents in a plurality of formats, tokenizing them into instances of concepts from an ontology, and assembling the resulting concepts into predicates. The ontological parser has two major functional elements, a sentence lexer and a parser. The sentence lexer takes a sentence and converts it into a sequence of ontological entities that are tagged with part-of-speech information. The parser converts the sequence of ontological entities into predicate structures using a two-stage process that analyzes the grammatical structure of the sentence, and then applies rules to it that bind arguments into predicates.

A system, method, and computer program are disclosed for recognizing one or more words not listed in a dictionary database. One or more sequences of characters in the word are checked to determine a probability that the word is valid. A prefix removal process removes any prefixes from a word, and obtains information about the removed prefix. A suffix removal process removes any suffixes from the word, and obtains information about the removed suffix. A root process obtains information about a root word from the dictionary database. A combination process then determines if the prefix, the root, and the suffix can be combined into a valid word as defined by one or more combination rules, obtains one or more of the possible parts of speech of the valid word, and stores the parts of speech with the valid word in the dictionary database.

In the present invention, a textual document is syntactically analyzed and knowledge is constructed from a single word or plural words. The knowledge is then marked, from the broken down knowledge (represented by the underscores in FIG. 1) or from a part-of-speech, as a related object (node) or a relation (edge) (represented by ‘n’ or ‘e’ shown in FIG. 1). In other words, in the present invention a textual document is treated as knowledge constructed from a single word or plural words. The knowledge extracted from the textual document is structured to form a knowledge structure (such as a graph structure constituted from nodes and edges). At least one link can be established between each of the knowledge structure elements and a semantically closest concept entry in a hierarchical concept dictionary.

Methods and apparatuses to assign part-of-speech tags to words are described. An input sequence of words is received. A global fabric of a corpus having training sequences of words may be analyzed in a vector space. A global semantic information associated with the input sequence of words may be extracted based on the analyzing. A part-of-speech tag may be assigned to a word of the input sequence based on POS tags from pertinent words in relevant training sequences identified using the global semantic information. The input sequence may be mapped into a vector space. A neighborhood associated with the input sequence may be formed in the vector space wherein the neighborhood represents one or more training sequences that are globally relevant to the input sequence.

A system and method for natural language processing of queries are provided. A lexicon includes text elements that are recognized as being a proper noun when capitalized. A natural language query includes a sequence of text elements including words. The query is processed. The processing includes a preprocessing step, in which part of speech features are assigned to the text elements in the query. This includes identifying, from a lexicon, a text element in the query which starts with a lowercase letter and assigning recapitalization information to the text element in the query, based on the lexicon. This information includes a part of speech feature of the capitalized form of the text element. Then parts of speech for the text elements in the query are disambiguated, which includes applying rules for recapitalizing text elements based on the recapitalization information.

A method for parsing a computerized text, the method including preparing a set of logical rules, using logical grammatical links, for parsing a text, using the logical rules to identify a part of speech of each word of text and all links between the words in the text, and labeling the links as grammatically correct links or grammatically incorrect links for correction, so as to parse substantially every word in the text.

An acronym expansion system of the present invention receives electronic documents and extracts acronyms and their corresponding expansions. A part-of-speech tagger decomposes text into string tokens or words and tags them with their part-of-speech, while an acronym identifier determines whether a word is a potential acronym based on various conditions. An expansion identifier retrieves lists of words preceding and following a potential acronym to search for the expansion. The resulting word lists are examined sequentially to identify and retrieve an expansion for the potential acronym. An expansion extractor receives the potential acronym and a processed word list to retrieve the expansion of the potential acronym from that list. The extractor may utilize information from prior search iterations, and verifies an extracted expansion against a set of rules to remove spurious expansions.

The invention discloses a sentiment analysis method oriented to a micro-blog short text. The method comprises the following steps: step 1, collecting micro-blog data including keywords so as to store in a database; step 2, pre-processing the micro-blog data; step 3, loading associated dictionaries; step 4, processing sentence division and filtering sentences which do not include user configuration keywords; step 5, processing word division to the sentences including the keywords and labeling parts of speech; step 6, processing dependency sentence structure analysis to the sentences including subjects by a sentence structure analyzing tool; step 7, judging the polarity of each sentence including subject words; and step 8, judging the polarity of a whole micro-blog after judging the polarities of all sentences including the subject words. According to the sentiment analysis method provided by the invention, sentiment analysis is more specific, so that users can know sentiment attitude of concerned aspects from the micro-blog.

Disclosed is a method for converting a plurality of words or sign language gestures into one or more sentences. The method involves the steps of: obtaining a plurality of words; assigning a part of speech tag to each of said words; assigning a sentence structure tag to said plurality of words; and parsing said words into one or more sentences based on a predefined sentence structure. The method can be implemented by a computer to provide a translator that more accurately reflects the natural language of the original text.

The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.

A method and apparatus automatically build a database by automatically assigning links to an expert, pushing content to an expert, providing expert annotation, and linking the content to an annotation database. A term is selected by applying rules, such as, the term not previously existing in the database, an unusually high frequency of the term, the term is an article or the term is an unusual part of speech. An advertiser can sponsor the term, for example, by having a banner ad automatically pop-up on a keyword search. Content windows can be attached to the term, the content window containing information such as definitions, related products or services, sponsorship information, information from content syndicators, translations and reference works.

Aspects of the invention present a system and methods to analyze textual communications, which include cognitive as well as emotive content. Generally accepted communication models and principles are used to create communication unique response templates which responders can use to complete a comprehensive, thoughtful, emotively validating response message. An embodiment is comprised of parsing and tokenizing the textual communication into the parts of speech, selecting subject matter from the tokenized parts of speech, fetching starter sentence string fragments from pre-stored data structures, concatenating the fragment strings with selected subject matter or emotive content into grammatical response sentence fragment strings, opening a response file or output device into which synthesized starter response sentence string fragments are written, such that the application systematically processes the complete textual communication and synthesizes communication unique response templates populated with response sentence string fragments in accordance with effective communication principles.

This invention provides a method and system for analyzing and deriving analytical insights from textual information. The information structuration process determines the structure in which the text information is rendered. A cyclical extraction process using the parameters of co-frequency, co-dependency, and co-relatedness and parts of speech, determines various textual aspects and their subcomponents such as themes and dimensions. Using the subcomponents of the textual aspects, relationship maps are built, disambiguated and ranked. A text analytics and decision support matrix is created using the ranked relations, thereby providing a highly relevant result set to the user's information need. A multidimensional navigation matrix is created that helps a user navigate across dimensions.

A computer-assisted method for discovering topics and categorizing contents in a document includes the steps of calculating an importance score for a term based on grammatical roles, parts of speech, and semantic attributes, selecting terms based on the importance score values of the respective terms, and outputting terms comprising the selected term to represent topics in the document, and building a category structure based on the selected terms.

A method of semantic profiling of documents comprises receiving a document to be profiled, the document comprising a plurality of terms, for each of at least a portion of the plurality of terms in the document determining a part of speech and a grammatical function of the term, obtaining senses of the term, selecting a sense as a most likely meaning of the term, and calculating an information value of the term, and generating a semantic profile of the document comprising at least some of the calculated information values.

A method to extract new keywords based on word frequency and multiple grammars is provided, which belongs to the technology field of a natural language processing, and is characterized by extracting the potential models of part of speech of the multiple grammars of the keywords by researching characteristic part of speech of the keywords and adopting computer to assist excavation and taking the models as the basis of the keywords to extract arithmetic. When extracting the new keywords, firstly excavating the multiple phrases in text in accordance with the potential models of part of speech and extract candidate word set of the keywords, and then excavating potential keywords not loading from titles and add the potential keywords to the candidate keyword set. The application brings forward an improved single text word frequency/inverse text frequency value (tf/idf) format, introduces target-oriented characteristics, grades the candidate keywords, obtains the order of the candidate keywords and gives the keywords of news document after optimizing the results. Compared with the traditional keyword extraction method based on single text word frequency/inverse text frequency value (tf/idf), the method has higher recall rate under the condition of the same precision.

A hybrid approach to improve handwriting recognition and voice recognition in data process systems is disclosed. In one embodiment, a front end is used to recognize strokes, characters and/or phonemes. The front end returns candidates with relative or absolute probabilities of matching to the input. Based on linguistic characteristics of the language, e.g. alphabetical or ideographic language for the words being entered, e.g. frequency of words and phrases being used, likely part of speech of the word entered, the morphology of the language, or the context in which the word is entered), a back end combines the candidates determined by the front end from inputs for words to match with known words and the probabilities of the use of such words in the current context.

Method and apparatus for providing a personalized self-support service to a user of an online application coupled with an online community forum. Embodiments include obtaining a plurality of questions from the online community forum and obtaining historical user data. Embodiments further include identifying one or more part-of-speech words in the plurality of questions and generating a high-dimensional vector for each question of the plurality of questions based on a frequency of the one or more part-of-speech words. Embodiments further include identifying one or more user features of the plurality of users based on the historical user data and establishing, based on the historical user data, one or more statistical correlations between user features and part-of-speech words. Embodiments further include training a predictive model based on the one or more statistical correlations. Embodiments further include using the predictive model to predict to provide one or more relevant questions to the user.