205 results about "Paraphrase" patented technology

Systems and methods for providing hands-free reading of content comprising: identifying a plurality of data items for presentation to a user, the plurality of data items associated with a domain-specific item type and sorted according to a particular order; based on the domain-specific item type, generating a speech-based overview of the plurality of data items; for each of the plurality of data items, generating a respective speech-based, item-specific paraphrase for the data item based on respective content of the data item; and providing, to a user through the speech-enabled dialogue interface, the speech-based overview, followed by the respective speech-based, item-specific paraphrases for at least a subset of the plurality of data items in the particular order.

A synthetic speech system includes a phoneme segment storage section for storing multiple phoneme segment data pieces; a synthesis section for generating voice data from text by reading phoneme segment data pieces representing the pronunciation of an inputted text from the phoneme segment storage section and connecting the phoneme segment data pieces to each other; a computing section for computing a score indicating the unnaturalness of the voice data representing the synthetic speech of the text; a paraphrase storage section for storing multiple paraphrases of the multiple first phrases; a replacement section for searching the text and replacing with appropriate paraphrases; and a judgment section for outputting generated voice data on condition that the computed score is smaller than a reference value and for inputting the text after the replacement to the synthesis section to cause the synthesis section to further generate voice data for the text.

A method, system, and computer program product for autonomously transcribing and building tagging data of a conversation. A corpus processing agent monitors a conversation and utilizes a speech recognition agent to identify the spoken languages, speakers, and emotional patterns of speakers of the conversation. While monitoring the conversation, the corpus processing agent determines emotional patterns by monitoring voice modulation of the speakers and evaluating the context of the conversation. When the conversation is complete, the corpus processing agent determines synonyms and paraphrases of spoken words and phrases of the conversation taking into consideration any localized dialect of the speakers. Additionally, metadata of the conversation is created and stored in a link database, for comparison with other processed conversations. A corpus, a transcription of the conversation containing metadata links, is then created. The corpus processing agent also determines the frequency of spoken keywords and phrases and compiles a popularity index.

A system is disclosed for selectively applying a paraphrase alternation pattern to a textual input. The system includes a pattern identification component for processing a collection of data and identifying a plurality of potentially applicable paraphrase alternation patterns. A context model provides an objective frame of reference in which to compare one or more of the plurality of potentially applicable paraphrase alternation patterns to the textual input to determine whether the pattern can be applied without changing meaning. A language model provides a principled basis for determining the boundaries of the text segment to be modified.

A synthetic speech system includes a phoneme segment storage section for storing multiple phoneme segment data pieces; a synthesis section for generating voice data from text by reading phoneme segment data pieces representing the pronunciation of an inputted text from the phoneme segment storage section and connecting the phoneme segment data pieces to each other; a computing section for computing a score indicating the unnaturalness of the voice data representing the synthetic speech of the text; a paraphrase storage section for storing multiple paraphrases of the multiple first phrases; a replacement section for searching the text and replacing with appropriate paraphrases; and a judgment section for outputting generated voice data on condition that the computed score is smaller than a reference value and for inputting the text after the replacement to the synthesis section to cause the synthesis section to further generate voice data for the text.

A computer-implemented method is disclosed for determining whether to apply a given paraphrase alternation pattern to an input string. The method includes generating a context model and applying the context model to determine whether the given paraphrase alternation pattern can be applied to the input string so as to preserve meaning.

A communication supporting apparatus includes an input accepting unit that accepts a source language sentence to be translated input by a user; a paraphrase knowledge storing unit that stores paraphrase knowledge in which a source language interpretation which is an interpretation of the semantic content of the source language sentence is associated with a paraphrase interpretation having the same semantic content as the source language interpretation and a different expression form; a source language analyzing unit that analyzes the semantic content of the input source language sentence and outputs the source language interpretation; a paraphrasing unit that obtains the paraphrase interpretation associated with the output source language interpretation from the paraphrase knowledge storing unit, and paraphrases the input source language sentence in a source language paraphrase sentence based on the obtained paraphrase interpretation; and a translation unit that translates the output source language interpretation into a first target language sentence and translates the obtained paraphrase interpretation into a second target language sentence.

A computer-implemented method is disclosed for applying a given paraphrase alternation pattern to an input string. The method includes generating a language model and applying the language model to determine how to apply the given paraphrase alternation pattern to the input string.

An “Interactive Word Lattice” provides a user interface for interacting with and selecting user-modifiable paths through a lattice-based representation of alternative suggested text segments in response to a user's text segment input, such as phrases, sentences, paragraphs, entire documents, etc. More specifically, the user input is provided to a trained paraphrase generation model that returns a plurality of alternative text segments having the same or similar meaning as the original user input. An interactive graphical lattice-based representation of the alternative text segments is then presented to the user. One or more words of each alternative text segment represents a “node” of the lattice, while each connection between nodes represents a lattice “edge. Both nodes and edges are user modifiable. Each possible path through the lattice corresponds to a different alternative text segment. Users select a path through the lattice to select an alternative text to the original input.

A method and computer program product for providing paraphrasing in a text-to-speech (TTS) system is provided. The method includes receiving an input text, parsing the input text, and determining a paraphrase of the input text. The method also includes synthesizing the paraphrase into synthesized speech. The method further includes selecting synthesized speech to output, which includes: assigning a score to each synthesized speech associated with each paraphrase, comparing the score of each synthesized speech associated with each paraphrase, and selecting the top-scoring synthesized speech to output. Furthermore, the method includes outputting the selected synthesized speech.

A computer-implemented method is disclosed for applying a given paraphrase alternation pattern to an input string. The method includes generating a language model and applying the language model to determine how to apply the given paraphrase alternation pattern to the input string.

A neural paraphrase generator receives a sequence of tuples comprising a source sequence of words, each tuple comprising word data element and structured tag element representing a linguistic attribute about the word data element. An RNN encoder receives a sequence of vectors representing a source sequence of words, and RNN decoder predicts a probability of a target sequence of words representing a target output sentence based on a recurrent state in the decoder. An input composition component includes a word embedding matrix and a tag embedding matrix, and receives and transforms the input sequence of tuples into a sequence of vectors by 1) mapping word data elements to word embedding matrix to generate word vectors, 2) mapping structured tag elements to tag embedding matrix to generate tag vectors, and 3) concatenating word vectors and tag vectors. An output decomposition component outputs a target sequence of tuples representing predicted words and structured tag elements, the probability of each single tuple from the output is predicted based on a recurrent state of the decoder.

A device for hiding information in a text comprises a mechanicanism for providing the text, means for linguistically analyzing the text to produce text components, for determining a plurality of formulation alternatives for the text by varying the order of the text components and, optionally, in addition by using synonyms for text components, determining every formulation alternative is grammatically correct for the text and has essentially the same meaning as the text. Certain partial information is allocated to every sequence and / or to every synonym or to every paraphrase.

The present invention is a distribution network cable-line mixed fault circuit selection method by using HHT detection technology. The invention uses HHT singularity detection technology to calibrate fault occurring time accurately, and implements circuit selection according to a principle that, when a fault occurs transient fault zero-sequence current component of the fault circuit and the regular circuit is opposite in direction. The specific method is using HHT to proceed EMD decomposition to the sampling signal of before and after 1 / 4 period each circuit fault zero-sequence current that is morphological filter pretreated, obtaining highest frequency IMF component of each circuit fault zero-sequence current and proceeding a first-order backward difference treatment to the IMF component, comparing the polar mutation of the fault zero-sequence current IMF component at fault moment, and then forming a circuit selection criterion. Analysis and simulation of the principle shows that, using fault information of 1 / 4 period after the fault to select circuit can provide an accurate and reliable circuit selection result and avoid effects of paraphrase and CT saturation on circuit selection accrracy.

The invention discloses a method for dynamic construction of a professional field mapping knowledge domain based on term paraphrase knowledge units and relates to the field of computer information management and information processing. The method is characterized in that a natural knowledge processing technology is used to extract and update knowledge units automatically from a real text; real contents of professional knowledge can be reflected by finer granularity contents; dynamic updating and management can be achieved; traditional problems such as insufficient timeliness, excessive subjectivity and difficult updating and maintenance caused by pure dependence on manual judgment could be solved; and a better technological manner can be provided for construction of a large knowledge library in professional fields. In addition, a mesh-shaped topological structure is adopted, so correlation between the knowledge units is closer, and semantic dimensions become diversified; a visualized knowledge map manner is used for visualized display, so a good knowledge foundation can be laid for automatic finding, inference and computation of knowledge; and the method can support engineering application effectively.

The present disclosure pertains to a paraphrase generation system. The system comprises one or more hardware processors and / or other components. The system is configured to obtain a training corpus. The training corpus comprises language and known paraphrases of the language. The system is configured to generate, based on the training corpus, a word-level attention-based model and a character-level attention-based model. The system is configured to provide one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models. The word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a character-level bidirectional LSTM network. The word-level and character level LSTM networks are generated based on words and characters in the training corpus. In some embodiments, the LSTM networks are stacked residual LSTM networks comprising residual connections between stacked layers of a given LSTM network.

A speech recognition dictionary creation device (10) that efficiently creates a speech recognition dictionary that enables even an abbreviated paraphrase of a word to be recognized with high recognition rate, the device including: a word division unit (2) that divides a recognition object made up of one or more words into constituent words; a mora string obtainment unit (3) that generates mora strings of the respective constituent words based on the readings of the respective divided constituent words; an abbreviated word generation rule storage unit (6) that stores a generation rule for generating an abbreviated word using moras; an abbreiivaed word generation unit (7) that generates candidate abbreviated words, each made up of one or more moras, by extracting moras from the mora strings of the respective constituent words and concatenating the extracted moras, and that generates an abbreviated word by applying the abbreviated word generation rule to such candidates; and a vocabulary storage unit (8) that stores, as the speech recognition dictionary, the generated abbreviated word together with its recognition object.

The present invention provides a system and method associating the freeform speech commands with one or more predefined commands from a set of predefined commands. The set of predefined commands are stored and alternate forms associated with each predefined command are retrieved from an external data source. The external data source receives the alternate forms associated with each predefined command from multiple sources so the alternate forms represent paraphrases of the predefined command. A representation including words from the predefined command and the alternate forms of the predefined command, such as a vector representation, is generated for each predefined command. A similarity value between received speech data and each representation of a predefined command is computed and the speech data is classified as the predefined command whose representation has the highest similarity value to the speech data.

A system is disclosed for selectively applying a paraphrase alternation pattern to a textual input. The system includes a pattern identification component for processing a collection of data and identifying a plurality of potentially applicable paraphrase alternation patterns. A context model provides an objective frame of reference in which to compare one or more of the plurality of potentially applicable paraphrase alternation patterns to the textual input to determine whether the pattern can be applied without changing meaning. A language model provides a principled basis for determining the boundaries of the text segment to be modified.

An “Interactive Word Lattice” provides a user interface for interacting with and selecting user-modifiable paths through a lattice-based representation of alternative suggested text segments in response to a user's text segment input, such as phrases, sentences, paragraphs, entire documents, etc. More specifically, the user input is provided to a trained paraphrase generation model that returns a plurality of alternative text segments having the same or similar meaning as the original user input. An interactive graphical lattice-based representation of the alternative text segments is then presented to the user. One or more words of each alternative text segment represents a “node” of the lattice, while each connection between nodes represents a lattice “edge. Both nodes and edges are user modifiable. Each possible path through the lattice corresponds to a different alternative text segment. Users select a path through the lattice to select an alternative text to the original input.

A natural language question answering system and method, and a paraphrase module are provided. The natural language question answering system includes a conversion module configured to generate a plurality of modified questions by paraphrasing a user's question; a plurality of question answering engines configured to receive each of the user's question and the modified questions, and select candidate answers corresponding to each of the user's question and the modified questions; and a detection module configured to detect at least one among the selected candidate answers as an answer.

The invention provides a word input method and an input method system having a translation function. The word input method comprises the following steps of: receiving a coded string input by a user; dissolving the coded string and obtaining a syllable unit sequence of a source language corresponding to the coded string; converting the syllable unit sequence of the source language and obtaining a syllable unit sequence of a target language; converting the syllable unit sequence of the target language and obtaining a transliteration result, and displaying the transliteration result; and outputting the appointed transliteration result according to an instruction of the user. In the word input method, a mapping relation between pronunciations of the two languages is constructed, so an effect that the user can obtain a correct spelling result through pronunciation can be achieved; under the help of the input method system, the user who forgets spelling can input a correctly spelled word or sentence; furthermore, some words which cannot be paraphrased or the paraphrase is not correct enough can be translated more accurately.

A method, system, and computer program product for autonomously transcribing and building tagging data of a conversation. A corpus processing agent monitors a conversation and utilizes a speech recognition agent to identify the spoken languages, speakers, and emotional patterns of speakers of the conversation. While monitoring the conversation, the corpus processing agent determines emotional patterns by monitoring voice modulation of the speakers and evaluating the context of the conversation. When the conversation is complete, the corpus processing agent determines synonyms and paraphrases of spoken words and phrases of the conversation taking into consideration any localized dialect of the speakers. Additionally, metadata of the conversation is created and stored in a link database, for comparison with other processed conversations. A corpus, a transcription of the conversation containing metadata links, is then created. The corpus processing agent also determines the frequency of spoken keywords and phrases and compiles a popularity index.

A computer based natural language processing method for identifying paraphrases in corpora using statistical analysis comprises deriving a set of starting paraphrases (SPs) from a parallel corpus, each SP having at least two phrases that are phrase aligned; generating a set of paraphrase patterns (PPs) by identifying shared terms within two aligned phrases of an SP, and defining a PP having slots in place of the shared terms, in right hand side (RHS) and left hand side (LHS) expressions; and collecting output paraphrases (OPs) by identifying instances of the PPs in a non-parallel corpus. By using the reliably derived paraphrase information from a small parallel corpus to generate the PPs, and extending the range of instances of the PPs over the large non-parallel corpus, better coverage of the paraphrases in the language and fewer errors are encountered.

A system and method of creating the natural language understanding component of a speech / text dialog system. The method involves a first step of defining user intent in the form of an intent flow graph. Next, (context, intent) pairs are created from each of the plurality of intent flow graphs and stored in a training database. A paraphrase task is then generated from each (context, intent) pair and also stored in the training database. A zero-shot intent recognition model is trained using the plurality of (context, intent) pairs in the training database to recognize user intents from the plurality of paraphrase tasks in the training database. Once trained, the zero-shot intent recognition model is applied to user queries to generate semantic outputs.

The invention provides a terms disambiguation method based on a semantic dictionary. In the method, term concept relevance is calculated to realize pretreatment on automatic text summarization, namely term disambiguation; the correlativity of concepts is used for realizing the term disambiguation method; requirements of the concept, concept paraphrase, synonym of the concept, expanded paraphrase of the concept, synset of expanded concept and other factors as well as sentence coherence are comprehensively considered; and a correlation degree calculation formula of the concept and a backtracking method are used for selecting the optimum meaning of a word, thus realizing the semantic disambiguation based on the context. An experiment proves that recall and accuracy of the semantic disambiguation can be improved and the method can be better used in acquisition of text summarization.

A language listening and speaking teaching system and method that utilize a random tests function to provide full-scale and various language training subjects and enable a learner to set up the listening and speaking training process according to his / her preference and create a more well-chosen shadowing learning process. Moreover, it assists a learner by enhancing and deepening the listening and speaking training content through an instant paraphrase and definition function, following completion of the shadowing learning process.

An automatic paraphrase acquisition technique is provided. A common theme of the various embodiments described herein resides in careful design of simple tasks that can elicit the necessary information for the automated process. These tasks are performed quickly and inexpensively. By gathering the results produced, paraphrases can be generated automatically using the method and / or system.

The invention provides a multilingual dictionary establishing device which may comprises a monolingual dictionary module, a keyword extraction module, a bilingual dictionary module and a translation confirmation module. The monolingual dictionary module selects words from a preset monolingual dictionary and obtains paraphrases of each sense corresponding to the words; the keyword extraction module extracts key words from the paraphrases; the bilingual dictionary module inquires out translation words of the words from a preset bilingual dictionary, wherein one language of the bilingual dictionary is the same with the language of the monolingual dictionary; and the translation confirmation module calculates similarities of the translation words with the words and the key words so as to select the final translation words corresponding to each sense for the words from the translation words and generate the multilingual dictionary. The invention further provides a multilingual dictionary establishing method. According to the device and the method, the multilingual dictionary can be established automatically, manpower and material resources for dictionary establishment are saved, the accuracy of the generated multilingual dictionary is guaranteed, and the compilation of the multilingual dictionary can be finished based on ordinary monolingual and bilingual dictionaries.