International Business Machines Corporation

Nuance Communications, Inc.

Shenghua Bao

Zhong Su

Jian Ye Chen

Yong Qin

Zhiwei Shuang

Qin Shi

William F Ganong, Iii

Wen Liu

Shi Lei Zhang

Cartic Ramakrishnan

Liu Wen

Shilei Zhang

Dong Wang

Rui Ma

Ying Chen

Anshu Narendra Jain

Maia A Smith

Li Ni Zhang

Xin Yang

Xiao Xun Zhang

Chunhua Tian

Meenakshi Nagarajan

Richard L Martin

John Christian Unterholzner

Cheng Lu

Neil S Bhargava

Lu Cheng En

The embodiments relate to generating hierarchical patterns based on a corpus of text. The corpus is analyzed, which includes extracting a set of features of the corpus. A set of grammatical patterns are generated based on the extracted features. The set of grammatical patterns includes at least one grammatical pattern generated from an internal pattern and at least one grammatical pattern generated from an external pattern. The grammatical patterns of the set are organized into a hierarchy and/or are ranked. The hierarchy and/or ranking are visually displayed.

Hierarchical target centric pattern generation

A method, a computing system and a computer program product are provided. A computing system identifies elements within a collection of medical documents. The elements include patients, adverse events and medical drugs. The medical documents are analyzed by the computer system to determine associations between the identified medical drugs and corresponding identified adverse events. The identified elements and the determined associations may be encoded as features by the computing system. The computing system identifies portions of the medical documents as containing the identified elements and the determined associations. The computing system generates a classification model based at least on the encoded features associated with the identified portions for identifying medical case safety reports within medical documents. The classification model is applied to a new document to determine a classification of the new document with respect to a medical case safety report.

Cognitive framework to identify medical case safety reports in free form text

Mechanisms are provide for implementing a context aware abbreviation detection and annotation operation. An instance of a full name of an entity is identified in received content and analysis of a context window associated with the instance of the full name of the entity is performed to identify a presence of a pattern of content representative of an abbreviation. An abbreviation is identified as being present in association with the instance of the full name of the entity based on results of the analysis of the context window and a mapping data structure that maps the full name of the entity to the abbreviation is generated. The received content is annotated based on the mapping data structure to thereby generate abbreviation annotations for the received content. The annotated received content is output for use by a cognitive system to perform a cognitive operation based on the annotated received content.

Dynamic context aware abbreviation detection and annotation

Techniques disclosed herein include systems and methods for open-domain voice-enabled searching that is speaker sensitive. Techniques include using speech information, speaker information, and information associated with a spoken query to enhance open voice search results. This includes integrating a textual index with a voice index to support the entire search cycle. Given a voice query, the system can execute two matching processes simultaneously. This can include a text matching process based on the output of speech recognition, as well as a voice matching process based on characteristics of a caller or user voicing a query. Characteristics of the caller can include output of voice feature extraction and metadata about the call. The system clusters callers according to these characteristics. The system can use specific voice and text clusters to modify speech recognition results, as well as modifying search results.

Speaker and call characteristic sensitive open voice search

A method and system for achieving emotional text to speech. The method includes: receiving text data; generating emotion tag for the text data by a rhythm piece; and achieving TTS to the text data corresponding to the emotion tag, where the emotion tags are expressed as a set of emotion vectors; where each emotion vector includes a plurality of emotion scores given based on a plurality of emotion categories. A system for the same includes: a text data receiving module; an emotion tag generating module; and a TTS module for achieving TTS, wherein the emotion tag is expressed as a set of emotion vectors; and wherein emotion vector includes a plurality of emotion scores given based on a plurality of emotion categories.

Method and system for achieving emotional text to speech utilizing emotion tags expressed as a set of emotion vectors

Method and system for achieving emotional text to speech utilizing emotion tags assigned to text data

A method, system and computer program product for identifying an advertisement in a web page. The method includes the steps of: receiving a sample page; analyzing a source code of the sample page to obtain a node feature of the sample page; analyzing the node feature using a preset rule to find a sample advertisement in the sample page; analyzing a first link of the sample advertisement to obtain a link mode of the sample advertisement; and utilizing the link mode to identify a second advertisement, where at least one of the steps is carried out using a computer device so that the advertisement in a web page is identified.

Method and system for identifying advertisement in web page

A method and an apparatus for recommending information to users within a social network. The method builds a recommendation list with at least one two-tuple, where each two-tuple comprises a target user name and an information item and ranks the recommendation list by using two-tuples in the recommendation list as a basic unit. By selecting a two-tuple in the recommendation list, the user can recommend a corresponding information item to a user represented by a target user name. An apparatus is also provided by using a builder for building for a user a recommendation list comprising at least one two-tuple and a sorter for ranking the recommendation list by using two-tuples in the recommendation list as a basic unit, such that, by selecting a two-tuple in the recommendation list.

Method and apparatus for recommending information to users within a social network

A method of automatically acquiring a feature segment in a music file includes receiving, with a processing device, a music file; converting the music file into a character string; evaluating at least one character string segment in the character string based on one or more music features; and determining, based on an evaluation result, at least one music segment corresponding to at least one character string segment in the character string as a feature segment.

Automatically acquiring feature segments in a music file

The present invention provides a method and apparatus for enhancing webpage browsing. The method of the invention includes a predicting step which predicts, for a first block in the webpage, a subsequent second block, based on a browsing history of blocks of webpages by at least one user; and a link generating step of automatically generating a link pointing to the second block based on a result of the predicting step. The apparatus includes: predicting means configured to predict, for a first block in the webpage, a subsequent second block, based on a browsing history of blocks of web pages by at least one user; and link generating means configured to automatically generate a link pointing to the second block based on a result of the predicting means.

Method and apparatus for enhancing webpage browsing

A method, system and computer program product for searching multilingual documents. The method includes the steps of: receiving a search request based on at least one language; searching a first relevant document using the search request where the first relevant document (1) is written in a first language and (2) has a first image; finding a second relevant document having a second image which is similar to the first image and is written in a second language; and searching a second relevant document using the search request.

Method and system for searching multilingual documents

Growing community of inventors

Beijing, China

Shenghua Bao