Yoshiyuki Okimoto has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
Abstract: A dialogue supporting apparatus is provided which carries out a trade-off between the speed of the translation process and the fluency of the translation result, in accordance with the contents of a dialogue.
Abstract: An input supporting device, which supports a user's input in the case where an information search is not progressing, so that the user can promptly obtain a result of the search, and includes: an input unit that receives an input of a search keyword; a search progress management unit that monitors progress of the search in a search device; and a search condition presentation unit which obtains an appropriate search condition based on the inputted search keyword and presents the obtained search condition to the user, in the case where the search is not progressing, while the search condition presentation unit includes: a categorized knowledge storage unit in which a category and a search keyword are stored in an associated manner; a category obtainment unit that obtains a category of the inputted search keyword with reference to the categorized knowledge storage unit; a search method storage unit in which a name of a search method and a category string are stored in an associated manner; a search method obtain
Abstract: To provide a dialog supporting apparatus which can support an on-going dialog so that the dialog is smoothly completed irrespective of the other party in the dialog. The dialog supporting apparatus 100 includes: an utterance receiving unit 101 and an utterance receiving unit 103 which respectively receive the utterances of the dialog participants and output the utterance information for identifying an utterance; an utterance outputting unit 102 and an utterance outputting unit 104 which respectively output the utterance information from the other participant in the dialog as an utterance; an utterance processing unit 105 which transforms the utterance identified by the utterance information into the other utterance form; a dialog history selection unit 107 which selects the optimum dialog history in the dialog history database 201; and an utterance prediction unit 106 which predicts utterances in the dialog based on the selected dialog history.
Abstract: 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 st
Abstract: A language model generation and accumulation apparatus (10) that generates and accumulates language models for speech recognition is comprised of: a higher-level N-gram generation and accumulation unit (11) that generates and accumulates a higher-level N-gram language model obtained by modeling each of a plurality of texts as a string of words including a word string class having a specific linguistic property; and a lower class dependent word N-gram generation and accumulation unit (12) that generates and accumulates a lower-level N-gram language model obtained by modeling a sequence of words included in each word string class.
Abstract: There is provided an information retrieval apparatus which can properly retrieve information associated with a user's preference from one of a plurality of data bases having different use frequencies. An information retrieval apparatus (100) includes: a retrieval instruction issue unit (102) which identifies one of an information source A data base (101A), an information source B data base (101B) and an information source C data base (101C) according to the user's operation; a retrieval keyword selection unit (105a) which preferentially selects, from a group of keywords indicating the user's preference, one or more strongly preferred keywords as many as a number associated with the use frequency of the data base identified by the retrieval instruction issue unit (102); and a retrieval unit (106) which retrieves information including the one or more keywords selected by the retrieval keyword selection unit (105a) from the data base identified by the retrieval instruction issue unit (102).