1. Articles in category: Summarization

    49-72 of 1867 « 1 2 3 4 5 6 ... 76 77 78 »
    1. Method and apparatus for summarizing communications

      A method, apparatus and computer program are provided for summarizing one or more communications. The method, apparatus and computer program process and/or facilitate a processing of one or more communications to generate at least one summary. The method, apparatus and computer program further cause, at least in part, a transformation of the at least one summary based, at least in part, on at least one narrative viewpoint. The method, apparatus and computer program further cause, at least in part, a presentation of the transformation.

      Read Full Article
    2. Generating News Headlines with Recurrent Neural Networks. (arXiv:1512.01712v1 [cs.CL])

      We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. We find that the model is quite effective at concisely paraphrasing news articles. Furthermore, we study how the neural network decides which input words to pay attention to, and specifically we identify the function of the different neurons in a simplified attention mechanism.

      Read Full Article
    3. Service monitoring interface

      One or more processing devices cause display of a service-monitoring page having a services summary region and a services aspects region. The services summary region contains an ordered plurality of interactive summary tiles, each summary tile corresponding to a respective service and providing a character or graphical representation of at least one value for an aggregate key performance indicator (KPI) characterizing the respective service as a whole. The services aspects region contains an ordered plurality of interactive aspect tiles, each aspect tile corresponding to a respective aspect KPI and providing a character or graphical representation of one or more values ...

      Read Full Article
      Mentions: KPI
    4. Inferring Interpersonal Relations in Narrative Summaries. (arXiv:1512.00112v1 [cs.CL])

      Characterizing relationships between people is fundamental for the understanding of narratives. In this work, we address the problem of inferring the polarity of relationships between people in narrative summaries. We formulate the problem as a joint structured prediction for each narrative, and present a model that combines evidence from linguistic and semantic features, as well as features based on the structure of the social community in the text.

      Read Full Article
    5. TGSum: Build Tweet Guided Multi-Document Summarization Dataset. (arXiv:1511.08417v1 [cs.IR])

      The development of summarization research has been significantly hampered by the costly acquisition of reference summaries. This paper proposes an effective way to automatically collect large scales of news-related multi-document summaries with reference to social media's reactions. We utilize two types of social labels in tweets, i.e., hashtags and hyper-links. Hashtags are used to cluster documents into different topic sets.

      Read Full Article
    6. Towards Universal Paraphrastic Sentence Embeddings. (arXiv:1511.08198v1 [cs.CL])

      In this paper, we show how to create paraphrastic sentence embeddings using the Paraphrase Database (Ganitkevitch et al., 2013), an extensive semantic resource with millions of phrase pairs. We consider several compositional architectures and evaluate them on 24 textual similarity datasets encompassing domains such as news, tweets, web forums, news headlines, machine translation output, glosses, and image and video captions.

      Read Full Article
    7. Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary.

      Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary.

      Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary.

      BMC Bioinformatics. 2015;16:149

      Authors: Xu Y, Chen L, Wei J, Ananiadou S, Fan Y, Qian Y, Chang EI, Tsujii J

      Abstract BACKGROUND: Electronic medical record (EMR) systems have become widely used throughout the world to improve the quality of healthcare and the efficiency of hospital services.

      Read Full Article
    8. Automated Methods for the Summarization of Electronic Health Records.

      Automated Methods for the Summarization of Electronic Health Records.

      Automated Methods for the Summarization of Electronic Health Records.

      J Am Med Inform Assoc. 2015 Apr 15;

      Authors: Pivovarov R, Elhadad N

      Abstract OBJECTIVES: This review examines work on automated summarization of electronic health record (EHR) data and in particular, individual patient record summarization. We organize the published research and highlight methodological challenges in the area of EHR summarization implementation.

      Read Full Article
    9. Construction of the integrated multicentre discharge summary database.

      Construction of the integrated multicentre discharge summary database.

      Construction of the integrated multicentre discharge summary database.

      Stud Health Technol Inform. 2013;192:1064

      Authors: Takahiro S, Shunsuke D, Shinsuke F, Yutaka H, Masayuki H, Yasushi M, Gen S, Mitsuhiro T, Shusaku T, Hideto Y, Katsuhiko T

      Abstract We started a multi-year project to collect discharge summaries from multiple hospitals and create a big text database to build a common document vector space, and develop various applications such as the autoselection of the disease.

      Read Full Article
    10. Method and apparatus for dynamic multiresolution clinical data display

      A multi-level information display system graphically represents clinical information for a user. The system includes a user interface providing clinical content to a user and accepting user input with respect to clinical content. The system also includes a graphical summary representation of a patient-related clinical data value. The graphical summary representation has one or more visible characteristics indicating an importance of the patient-related clinical data value. The system also includes a thumbnail trend view providing a graph of data elements used to provide the patient-related clinical data value shown in the graphical summary representation. The system further includes an originating ...

      Read Full Article
    11. Intelligent text-to-speech conversion

      Techniques for improved text-to-speech processing are disclosed. The improved text-to-speech processing can convert text from an electronic document into an audio output that includes speech associated with the text as well as audio contextual cues. One aspect provides audio contextual cues to the listener when outputting speech (spoken text) pertaining to a document. The audio contextual cues can be based on an analysis of a document prior to a text-to-speech conversion. Another aspect can produce an audio summary for a file. The audio summary for a document can thereafter be presented to a user so that the user can hear ...

      Read Full Article
    12. Self-learning methods for automatically generating a summary of a document, knowledge extraction and contextual mapping

      Advance Machine Learning or Unsupervized Machine Learning Techniques are provided that relate to Self-learning processes by which a machine generates a sensible automated summary, extracts knowledge, and extracts contextually related Topics along with the justification that explains "why they are related" automatically without any human intervention or guidance (backed ontology's) during the process. Such processes also relate to generating a 360-Degree Contextual Result (360-DCR) using Auto-summary, Knowledge Extraction and Contextual Mapping.

      Read Full Article
    13. System and method for grouping multiple streams of data

      A document clustering system and method of assigning a document to a cluster of documents containing related content are provided. Each cluster is associated with a cluster summary describing the content of the documents in the cluster. The method comprises: determining, at a document clustering system, whether the document should be grouped with one or more previously created cluster summaries, the previously created cluster summaries being stored in a memory in a B-tree data structure; and if it is determined that the document should not be grouped with the one or more previously created cluster summaries, then creating, at a ...

      Read Full Article
    14. Webinar: Translation Trends 2015

      Learn what 2015 holds for the future of translation. In this webinar hosted by MemSource, you will hear a summary of 2014 and catch a glimpse of what's in store for 2015. Panelists include Microsoft Translator's Chris Wendt, MemSource CEO David Canek, Torben Dahl Jensen from TextMinded, and Moravia's Jan Hofmeister. Ask your questions during the webinar, or in advance by posting them to @memsource on Twitter.

      Read Full Article
    15. Personalized News-Reading App Pipes Now Smartly Summarizes Articles, Without The Help Of Editors

      A personalized news reading app, Pipes, is now offering summaries of news stories to save mobile readers time while trying to catch up on-the-go. This is a big shift for the app, which launched earlier this year to offer a more mainstream-friendly way of consuming news and other topical information from a variety of sources, without having to understand the technicalities of using RSS or… Read ...

      Read Full Article
      Mentions: Google Yahoo anAND
    16. Aspect-based sentiment summarization

      Phrases in the reviews that express sentiment about a particular aspect are identified. Reviewable aspects of the entity are also identified. The reviewable aspects include static aspects that are specific to particular types of entities and dynamic aspects that are extracted from the reviews of a specific entity instance. The sentiment phrases are associated with the reviewable aspects to which the phrases pertain. The sentiment expressed by the phrases associated with each aspect is summarized, thereby producing a summary of sentiment associated with each reviewable aspect of the entity. The summarized sentiment and associated phrases can be stored and displayed ...

      Read Full Article
    17. Summarizing reviews

      Summarizing a set of reviews is disclosed. In some embodiments, a set of reviews is analyzed, e.g., by an at least partially automated process. A summary of the information included in the set of reviews is provided. The summary includes a visual indication of a range and distribution of opinions expressed in the set of reviews. In some embodiments, the set of reviews includes reviews from one or more members of an online or other user community, such as customers of an online store, subscribers to a podcast, blog, or other online source of content, etc.

      Read Full Article
    18. Signature generation using message summaries

      Systems and methods for processing a message are provided. A message may be processed to generate a message summary by removing or replacing certain words, phrases, sentences, punctuation, and the like. Message signatures based upon the message summary may be generated and stored in a signature database, which may be used to identify and/or classify spam messages. Subsequently received messages may be classified by signature and processed based on classification.

      Read Full Article
    49-72 of 1867 « 1 2 3 4 5 6 ... 76 77 78 »
  1. Categories

    1. Default:

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

  3. Organizations in the News

    1. (2 articles) Association for Computational Linguistics
    2. (2 articles) Stanford
    3. (1 articles) National Conference on Artificial Intelligence
    4. (1 articles) Smith
    5. (1 articles) Nigam
    6. (1 articles) Reuters
    7. (1 articles) Microsoft
    8. (1 articles) WordNet
    9. (1 articles) Emnlp
    10. (1 articles) Monsanto
    11. (1 articles) Information Retrieval
    12. (1 articles) Coling
  4. Locations in the News

    1. (2 articles) USA
    2. (1 articles) Argentina
    3. (1 articles) Romania
    4. (1 articles) Malaysia
    5. (1 articles) New York
    6. (1 articles) Idf
    7. (1 articles) Honolulu
    8. (1 articles) India
    9. (1 articles) Pune
    10. (1 articles) Bayes
    11. (1 articles) San Francisco
    12. (1 articles) Massachusetts
  5. People in the News

    1. (2 articles) Christopher Manning
    2. (1 articles) Rohini Srihari
    3. (1 articles) Andrew McCallum
    4. (1 articles) Susan Dumais
    5. (1 articles) Sholom M. Weiss
    6. (1 articles) John Platt
    7. (1 articles) J. L. Elman
    8. (1 articles) Tong Zhang
    9. (1 articles) Richard Socher
    10. (1 articles) A. McCallum
    11. (1 articles) Rosie Jones
    12. (1 articles) N. A. Smith