International Business Machines Corporation

Embodyme, Inc.

Issei Yoshida

Tohru Hasegawa

Shunsuke Ishikawa

Asako Ono

Kenta Watanabe

Hiroaki Uetsuki

Yasuyuki Tominaga

Masayuki A Suzuki

Kohichi Kamijoh

Daisuke Takuma

Tetsuya Nasukawa

Sachiko Yoshihama

Miki Ishikawa

Yohei Ikawa

Yuta Tsuboi

Risa Kawanaka

Ryuki Tachibana

Toyotaro Suzumura

Toru Nagano

Hiroshi Kanayama

Fumiko Satoh

Yoshinori Kabeya

Masayasu Muraoka

Ryosuke Kohita

Hideo Watanabe

Akiko Suzuki

Hiroaki Kikuchi

Hiroki Yanagisawa

Shoko Suzuki

Miki M Enoki

Kaoru Shinkawa

Raymond Harry Putra Rudy

Akiko Murakami

Yang Zhao

Dependency trees are generated for questions and answers of a question answering (QA) corpus in which the answers are associated with the questions. Generating the dependency trees includes identifying root nodes. A word near an identified root node of one of the questions is compared to words of answers associated with the one of the questions. The word is determined to be in less than a threshold number of the associated answers. The word is identified as a stop word.

Stop word detection for QA corpus

Frequent sequences extracted from a set of documents according to a common rule are obtained. Based on comparing occurrence frequencies of various sequences, confidence of the first frequent sequence being a label expression representing a document part in a target document is evaluated. Keywords are extracted from the target document based on evaluation of the confidence.

Text mining based on document structure information extraction

A computer-implemented method is provided for estimating output confidence of a black box Application Programming Interface (API). The method includes generating paraphrases for an input text. The method further includes calculating a distance between the input text and each respective one of the paraphrases. The method also includes sorting the paraphrases in ascending order of the distance. The method additionally includes selecting a top predetermined number of the paraphrases. The method further includes inputting the input text and the selected paraphrases into the API to obtain an output confidence score for each of the input text and the selected paraphrases. The method also includes estimating, by a hardware processor, the output confidence of the input text from a robustness of output scores of the input text and the selected paraphrases.

Estimating output confidence for black-box API

A computer-implemented method, a computer program product, and a computer system for dependency tree-based data augmentation for sentence well-formedness judgement. A computer applies a dependency parser to generate a dependency tree for a sentence. The computer removes one or more nodes in the dependency tree, according to a removal ratio for a predetermined rating score. The computer generates, from the dependency tree, a partial tree for the sentence. The computer outputs a rated sentence based on the partial tree. The rated sentence is used as training data.

Dependency tree-based data augmentation for sentence well-formedness judgement

A computer-implemented method for graphical user interface element accessibility is disclosed. The computer-implemented method includes generating a graphical user interface element rendered on a web page as a virtual button displayed on a display screen of a device. The virtual button is not rendered on the webpage and includes an invocable function mapped to the graphical user interface element. The computer-implemented method further includes moving the virtual button along a periphery of the display screen of the device. A rate at which the virtual button moves along the periphery of the display screen of the device is dynamically modified based on a detected identity of a user of the device.

Dynamic user interface pagination operation

A computer-implemented method is provided for data augmentation. The method includes receiving a set of different base models already pretrained and a set of different test cases. The method further includes collecting a plurality of prediction results of the set of different test cases from the set of different base models. The method also includes identifying a test case as a candidate for the data augmentation based on a number of models in the set of different base models which fail to solve the test case. The method additionally includes augmenting, by a processor device, the identified test case with additional data to form an augmented training dataset. The method further includes retraining at least some of the different base models with the augmented training dataset.

Data augmentation based on failure cases

A method is provided for dictionary expansion. The method acquires an object from a user and adds the object to a set of objects previously acquired from the user that form an expandable dictionary. The method calculates a centroid based on the set. The method calculates a similarity score of each of a plurality of objects relative to the centroid for each of a plurality of object features to calculate a weighted sum of similarity scores for each of the plurality of objects. The method presents candidate objects selected among the plurality of objects based on the weighted sum. The method acquires, from the user, a preferred candidate object among the candidate objects. The method updates weights of the plurality of features to maximize the weighed sum of similarity scores for the preferred candidate object. The method expands the dictionary by adding the preferred candidate object to the expandable dictionary.

User-centric optimization for interactive dictionary expansion

A method is provided for determining support of a hypothesis by opinion sentences. The method converts sentence structures in the opinion sentences using various sentence structure conversion methods to obtain converted opinion sentences. For each converted opinion sentence, the method calculates a difference between a proximity label value indicating proximity to the hypothesis and an intermediate score before and after a conversion, adopts the conversion responsive to a condition being met relative to the difference, and adopts the opinion sentence instead responsive to the condition being unmet. The method creates sub-opinions using the various methods applied to adopted conversions and opinion sentences, and obtains an intermediate score for each sub-opinion. The method represents an amount of support for the hypothesis by obtaining and displaying a final score for each adopted conversions and opinion sentences based on the intermediate scores for the sub-opinions and for adopted conversions and opinion sentences.

Optimized document score system using sentence structure analysis function

A system and method for expanding a question and answer (Q&A) database. The method includes obtaining a set of Q&A documents and speech recognition results, each Q&A document in the set having an identifier, and each speech recognition result having an identifier common with the identifier of a relevant Q&A document, and adding one or more repetition parts extracted from the speech recognition results to a corresponding Q&A document in the set to generate an expanded set of Q&A documents for increasing Q&A document extraction accuracy.

Expansion of a question and answer database

Methods and systems for information retrieval include analyzing audio data to produce word hypotheses. Displaying the word hypotheses in motion at different respective speeds at once across a graphical display. Information is retrieved in accordance with one or more selected terms from the displayed word hypotheses.

User interface for streaming spoken query

A method, computer program product and computer system are provided to promote device usage compliance. A processor retrieves a current position for a device. A processor determines at least one nearby location based on the current position of the device. A processor retrieves search data regarding the at least one nearby location. A processor determines compliance information regarding the at least one location based, at least in part, on the search data. A processor configures the device based on the compliance information regarding the at least one location.

Web-sourced device control

A method is provided for validating a hypothesis sentence. The method extracts, from a document database D using a hypothesis sentence that includes a causal part and a consequence part, a set D1 of documents related to the causal part. The method extracts, from set D1, a set S of sentences that include expressions of opinion. The method obtains a word list W of words that have a high co-occurrence in the set D1. The method selects, from the set S, a set S1 of sentences that are positionally close to any of the words in the word list W. The method selects, from the set S, a set S2 of sentences that are related to the words in the consequence part of the hypothesis. The method extracts and displays sentences included in both the set S1 and the set S2 as opinion sentences in relation to the hypothesis sentence.

Extracting important sentences from documents to answer hypothesis that include causes and consequences

A computer-implemented method for a user interface paging operation includes: generating a pagination design pattern rendered on a web page as a plurality of virtual buttons displayed on a display screen of a device, wherein each virtual button is mapped to actions related to graphical elements of the pagination design pattern; moving the series of virtual buttons about at least a portion of the periphery of the display screen of the device; locating the display of the plurality of virtual buttons to positions within a periphery of the display screen of the device; subsequent to locating the display of the plurality of virtual buttons to positions within the periphery of the display screen of the device, receiving user input specifying selection of a first virtual button of the plurality of virtual buttons; and responsive to receipt of the user input: performing the action mapped to the first virtual button.

A method is provided that stores, in a second memory, an index structure including, for each given word from among words included in documents, a group of document IDs of documents including the given word. The method stores an index structure subset in a main memory which is faster than secondary memory. The method acquires a keyword and identifies any documents including the keyword. The method finds top-K frequent words among the words included in the identified documents by: identifying, for each given group in descending order of the number of the documents IDs therein, the number of documents IDs of the identified documents in the given group, from the subset when the number of document IDs in the given group is within the range, and from the index structure otherwise; and presenting words of top-K groups with a largest amount of the document IDs identified.

Growing community of inventors

Tokyo, Japan

Issei Yoshida