1. Articles in category: Segmentation

    529-552 of 835 « 1 2 ... 20 21 22 23 24 25 26 ... 33 34 35 »
    1. System and method for text segmentation and display

      The present invention provides a system and method for dividing patent claims into segments for display. A segmentation engine of a computer program searches for transitional phrases or other strings and divides the patent claims into a segment for each claim. The segmentation engine also searches for dependency references. A display engine of the program uses the dependency data to display the claims in a tree structure. The segmentation also divides each claim into subsegments containing the various components of the claim. The subsegments of each claim are displayed in a tree structure nested within the tree structure of the ...
      Read Full Article
    2. Lymphocyte Cell Biology Research Database

      DUBLIN--(BUSINESS WIRE)--Maven Semantic (http://www.mavensemantic.com) announces updates to their Lymphocyte Cell Biology research database. The new database is now available to marketing, business development, competitor intelligence, KOL, medical affairs and related departments in the life sciences sector. The database currently tags 61,000 individuals working in ...
      Read Full Article
    3. Domain-specific Chinese word segmentation using suffix tree and mutual information

      Abstract  As the amount of online Chinese contents grows, there is a critical need for effective Chinese word segmentation approaches to facilitate Web computing applications in a range of domains including terrorism informatics. Most existing Chinese word segmentation approaches are either statistics-based or dictionary-based. The pure statistical method has lower precision, while the pure dictionary-based method cannot deal with new words beyond the dictionary. In this paper, we propose a hybrid method that is able to avoid the limitations of both types of approaches. Through the use of suffix tree and mutual information (MI) with the dictionary, our segmenter, called ...
      Read Full Article
    4. Frequent Words’ Grammar Information in Chinese Chunking

      In Chinese, frequent words, which always contain no significant information for information extraction, play an important role in the grammar structure of sentences. But the grammar information of these words is always ignored in Chinese segmentation. In this paper, for Chinese chunking, we dsesign an experiment to integrate the grammar information of frequent words and investigate the effect of this information on the chunking. We use conditional random fields for chunking, and rewrite the frequent words in the corpus to make them contain sentence structure information. The results show that the grammar information of frequent words, the number of which ...
      Read Full Article
    5. Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

      Abstract  A challenging problem in human action understanding is to jointly segment and recognize human actions from an unseen video sequence, where one person performs a sequence of continuous actions. In this paper, we propose a discriminative semi-Markov model approach, and define a set of features over boundary frames, segments, as well as neighboring segments. This enable us to conveniently capture a combination of local and global features that best represent each specific action type. To efficiently solve the inference problem of simultaneous segmentation and recognition, a Viterbi-like dynamic programming algorithm is utilized, which in practice is able to process ...
      Read Full Article
    6. Segmentation-based multi-class semantic object detection

      Abstract  In this paper we study the problem of the detection of semantic objects from known categories in images. Unlike existing techniques which operate at the pixel or at a patch level for recognition, we propose to rely on the categorization of image segments. Recent work has highlighted that image segments provide a sound support for visual object class recognition. In this work, we use image segments as primitives to extract robust features and train detection models for a predefined set of categories. Several segmentation algorithms are benchmarked and their performances for segment recognition are compared. We then propose two ...
      Read Full Article
      Mentions: Microsoft
    529-552 of 835 « 1 2 ... 20 21 22 23 24 25 26 ... 33 34 35 »
  1. Categories

    1. Default:

      Discourse, Entailment, Machine Translation, NER, Parsing, Segmentation, Semantic, Sentiment, Summarization, WSD
  2. Popular Articles

  3. Organizations in the News

    1. (40 articles) Microsoft
    2. (34 articles) Google
    3. (21 articles) Apac
    4. (20 articles) Nuance Communications
    5. (19 articles) Intel
    6. (19 articles) SMEs
    7. (18 articles) Healthcare
    8. (18 articles) Service
    9. (18 articles) IBM
    10. (17 articles) IBM Corporation
    11. (17 articles) Bfsi
    12. (15 articles) NLP
  4. Locations in the News

    1. (29 articles) India
    2. (23 articles) Japan
    3. (22 articles) China
    4. (19 articles) Pune
    5. (18 articles) New York
    6. (14 articles) Canada
    7. (13 articles) Germany
    8. (12 articles) Africa
    9. (12 articles) France
    10. (9 articles) Washington
    11. (9 articles) Massachusetts
    12. (9 articles) California
  5. People in the News

    1. (4 articles) Laura Wood