1. Articles in category: Discourse

    1-24 of 106 1 2 3 4 5 »
    1. Computer-implemented systems and methods for measuring discourse coherence

      Systems and methods are provided for automatically generating a coherence score for a text using a scoring model. A lexical chain is identified within a text to be scored, where the lexical chain comprises a set of words spaced within the text. A discourse element is identified within the text, where the discourse element comprises a word within the text. A coherence metric is determined based on a relationship between the lexical chain and the discourse element. A coherence score is generated using a scoring model by providing the coherence metric to the scoring model.

      Read Full Article
    2. Boston Launches Revolutionary ANNA Pascal XL Powered by 8 NVIDIA® Tesla® P100s

      St. Albans, United Kingdom -- Boston Limited is pleased to announce the launch of the Boston ANNA Pascal XL, the latest addition to its machine learning armoury, powered by eight NVIDIA Tesla P100 GPUs. The supersized GPU solution will have its world debut on Boston Limited's stand (428) at the GPU Technology Conference (GTC), San Jose, California , USA 9th-11th May. Accelerated solutions such as the Boston ANNA Pascal XL, are redefining what is possible for a broad range of industries.

      Read Full Article
    3. Breaking Data's Givemesport Partners with McLaren Racing for the World's Fastest Gamer Competition

      May 08, 2017 at 07:30 AM EDT Breaking Data's GIVEMESPORT Partners with McLaren Racing for the World's Fastest Gamer Competition GIVEMESPORT to market this ground-breaking eSports event to its massive worldwide audience on the web TORONTO, ONTARIO and LONDON, UNITED KINGDOM -- (Marketwired) -- 05/08/17 -- Breaking Data Corp. ( TSX VENTURE: BKD )(OTC PINK: BKDCD) ("Breaking Data" or the "Company") is pleased to announce that it has partnered with McLaren to market World's Fastest Gamer - the world's most intense and demanding competition for virtual racers. It's a contest that will see the winner offered the ...

      Read Full Article
      Mentions: London Company World
    4. Breaking Data's Givemesport Partners with McLaren Racing for the World's Fastest Gamer Competition / Givemesport to market this ground-breaking eSports event to its massive worldwide audience on the web

      Breaking Data's Givemesport Partners with McLaren Racing for the World's Fastest Gamer Competition / Givemesport to market this ground-breaking eSports event to its massive worldwide audience on the web

      Breaking Data's GIVEMESPORT Partners with McLaren Racing for the World's Fastest Gamer Competition / GIVEMESPORT to market this ground-breaking eSports event to its massive worldwide audience on the web TORONTO, ONTARIO and LONDON, UNITED KINGDOM -- (Marketwired) -- 05/08/17 -- Breaking Data Corp. (TSX VENTURE: BKD)(OTC PINK: BKDCD) ("Breaking Data" or the "Company") is pleased to announce that it has partnered with McLaren to market World's Fastest Gamer - the world's most intense and demanding competition for virtual racers. It's a contest that will see the winner offered the best job in eSports - a role with the ...

      Read Full Article
      Mentions: London Company World
    5. Breaking Data : Givemesport Partners with McLaren Racing for the World's Fastest Gamer Competition

      TORONTO, ONTARIO and LONDON, UNITED KINGDOM--(Marketwired - May 8, 2017) - Breaking Data Corp. (TSX VENTURE:BKD)(OTC PINK:BKDCD) ("Breaking Data" or the "Company") is pleased to announce that it has partnered with McLaren to market World's Fastest Gamer - the world's most intense and demanding competition for virtual racers. It's a contest that will see the winner offered the best job in eSports - a role with the Formula 1 team as one of its official simulator drivers.

      Read Full Article
      Mentions: London Company World
    6. Protagonist Platform launches to uncover customer narratives using machine learning

      Protagonist Platform launches to uncover customer narratives using machine learning

      Tags: ai , customer stories , machine learning , marketing , marketing technology , Marketing Weekly , martech , narrative analysis , NLP Image Credit: Shutterstock Despite the breadth and depth of the marketing technology universe and the emergence of AI and machine learning capabilities, marketing hasn’t really changed in hundreds of years. It has always been about understanding your customer and communicating with them efficiently and effectively.

      Read Full Article
      Mentions: NLP
    7. Theme 3: Things will get better

      Theme 3: Things will get better

      By Lee Rainie , Janna Anderson and Jonathan Albright The more hopeful among these respondents cited a series of changes they expect in the next decade that could improve the tone of online life. They believe: Technical and human solutions will arise as the online world splinters into segmented, controlled social zones with the help of artificial intelligence (AI ). Anti-harassment is a technologically solvable problem.

      Read Full Article
    8. Integrated word N-gram and class M-gram language models

      Systems and processes for discourse input processing are provided. In one example process, a discourse input can be received from a user. An integrated probability of a candidate word in the discourse input and one or more subclasses associated with the candidate word can be determined based on a conditional probability of the candidate word given one or more words in the discourse input, a probability of the candidate word within a corpus, and a conditional probability of the candidate word given one or more classes associated with the one or more words. A text string corresponding to the discourse ...

      Read Full Article
    9. Initial thoughts on fairness in paper recommendation?

      There are a handful of definitions of "fairness" lying around, of which the most common is disparate impact: the rate at which you hire members of a protected category should be at least 80% of the rate you hire members not of that category. (Where "hire" is, for our purposes, a prediction problem, and 80% is arbitrary.) DI has all sorts of issues, as do many other notions of fairness, but all the ones I've seen rely on a pre-ordained notion of "protected category".

      Read Full Article
      Mentions: Percy Liang NLP
    10. Fake News and Fake Solutions: How Do We Build a Civics of Trust?

      Fake News and Fake Solutions: How Do We Build a Civics of Trust?

      Posted 20 March 2017 16:37 GMT Share this: Protesters fly a flag upside down as a signal of distress outside the offices of The Washington Post in Washington D.C. on Inauguration Day, January 20, 2017. Photo: Ivan Sigal. In his recent manifesto , Mark Zuckerberg asserts that the response to our dysfunctional and conflict-ridden politics is to build a stronger global community based on ubiquitous interconnection.

      Read Full Article
    11. Fake News and Fake Solutions: How Do We Build a Civics of Trust? · Global Voices

      Fake News and Fake Solutions: How Do We Build a Civics of Trust? · Global Voices

      Posted 17 March 2017 21:24 GMT Share this: Protesters fly a flag upside down as a signal of distress outside the offices of The Washington Post in Washington D.C. on Inauguration Day, January 20, 2017. Photo: Ivan Sigal. In his recent manifesto , Mark Zuckerberg asserts that the response to our dysfunctional and conflict-ridden politics is to build a stronger global community based on ubiquitous interconnection.

      Read Full Article
    12. Using domain knowledge and domain-inspired discourse model for coreference resolution for clinical narratives.

      Using domain knowledge and domain-inspired discourse model for coreference resolution for clinical narratives.

      J Am Med Inform Assoc. 2013 Mar-Apr;20(2):356-62

      Authors: Jindal P, Roth D

      Abstract OBJECTIVE: This paper presents a coreference resolution system for clinical narratives. Coreference resolution aims at clustering all mentions in a single document to coherent entities. MATERIALS AND METHODS: A knowledge-intensive approach for coreference resolution is employed.

      Read Full Article
    13. Methods for automated essay analysis

      Systems and methods for creating a mathematical model for use in identifying discourse elements are described. A plurality of first essays relating to a particular subject are received, where each first essay is in an electronic format. Annotations for each first essay are received, where each annotation identifies at least one discourse element. Features are identified with a processor, where each feature is exhibited by at least one identified discourse element. Empirical frequencies are computed with a processor, where each empirical frequency relates to the presence of a feature with respect to the identified discourse elements across the plurality of ...
      Read Full Article
    14. Automatic discourse connective detection in biomedical text.

      Related Articles Automatic discourse connective detection in biomedical text. J Am Med Inform Assoc. 2012 Sep-Oct;19(5):800-8 Authors: Ramesh BP, Prasad R, Miller T, Harrington B, Yu H Abstract OBJECTIVE: Relation extraction in biomedical text mining systems has largely focused on identifying clause-level relations, but increasing sophistication demands the recognition of relations at discourse level. A first step in identifying discourse relations involves the detection of discourse connectives: words or phrases used in text to express discourse relations. In this study supervised machine-learning approaches were developed and evaluated for automatically identifying discourse connectives in biomedical text. MATERIALS AND ...
      Read Full Article
    15. A Novel System for Unlabeled Discourse Parsing in the RST Framework

      This paper presents UDRST, an unlabeled discourse parsing system in the RST framework. UDRST consists of a segmentation model and a parsing model. The segmentation model exploits subtree features to rerank N-best outputs of a base segmenter, which uses syntactic and lexical features in a CRF framework. In the parsing model, we present two algorithms for building a discourse tree from a segmented text: an incremental algorithm and a dual decomposition algorithm. Our system achieves 77.3% in the unlabeled score on the standard test set of the RST Discourse Treebank corpus, which improves 5.0% compared to HILDA [6 ...
      Read Full Article
    16. Conceptual recurrence plots: revealing patterns in human discourse.

      Related Articles Conceptual recurrence plots: revealing patterns in human discourse. IEEE Trans Vis Comput Graph. 2012 Jun;18(6):988-97 Authors: Angus D, Smith A, Wiles J Abstract Human discourse contains a rich mixture of conceptual information. Visualization of the global and local patterns within this data stream is a complex and challenging problem. Recurrence plots are an information visualization technique that can reveal trends and features in complex time series data. The recurrence plot technique works by measuring the similarity of points in a time series to all other points in the same time series and plotting the results ...
      Read Full Article
      Mentions: Smith Medline
    17. On the Syntax and Translation of Finnish Discourse Clitics

      Finnish has a set of morphemes called discourse clitics, which attach to words and express things like contrasting and reminding. This paper builds a formal grammar to specify the syntax and morphology of these clitics. The grammar is written in GF, Grammatical Framework, which has a distinction between abstract syntax (tree structures) and concrete syntax (surface structures such as strings). The abstract syntax of clitics defines their contribution to the discourse semantics of sentences, in particular the topic-focus structure. The concrete syntax defines the realization in Finnish. We also show another concrete syntax, for English, which makes it possible to ...
      Read Full Article
    18. A computational model for the identification and assessment of structural similarities in argumentative discourses

      Abstract  Contemporary argumentation systems provide limited or no support for argument and related information processing. This paper presents a generic computational model that is able to identify and assess structural similarities in argumentative discourses. Focusing on the structure of such discourses, we sketch representative scenarios where the proposed model can be applied to a wide range of argumentation systems in order to define, elaborate and mine meaningful argumentation patterns. We argue that the proposed model contributes to both theoretical and practical aspects of argumentation. Content Type Journal ArticlePages 1-23DOI 10.1007/s10844-012-0212-9Authors George Gkotsis, Industrial Management and Information Systems Lab ...
      Read Full Article
    19. Multi-Dimensional Analysis of Political Language

      This paper presents a method for the valuation of discourses from different linguistic perspectives: lexical, syntactic and semantic. We describe a platform discourse analysis tool (DAT) which integrates a range of language processing tools with the intent to build complex characterisations of the political discourse. The idea behind this construction is that the vocabulary and the clause structure of the sentence betray the speaker’s level of culture, while the semantic classes mentioned in a speech characterises the speaker’s orientation. When the object of study is the political discourse, an investigation on these dimensions could put in evidence features ...
      Read Full Article
    20. A Computational Analysis of Collective Discourse. (arXiv:1204.3498v1 [cs.SI])

      This paper is focused on the computational analysis of collective discourse, a collective behavior seen in non-expert content contributions in online social media. We collect and analyze a wide range of real-world collective discourse datasets from movie user reviews to microblogs and news headlines to scientific citations. We show that all these datasets exhibit diversity of perspective, a property seen in other collective systems and a criterion in wise crowds. Our experiments also confirm that the network of different perspective co-occurrences exhibits the small-world property with high clustering of different perspectives. Finally, we show that non-expert contributions in collective discourse ...
      Read Full Article
    21. Multiple Level of Referents in Information State

      As we strive for sophisticated machine translation and reliable information extraction, we have launched a subproject pertaining to the practical elaboration of “intensional” levels of discourse referents in the framework of a representational dynamic discourse semantics, the DRT-based [14] [2], and the implementation of resulting representations within a complete model of communicating interpreters’ minds as it is captured formally in by means of functions σ, α, λ and κ [5]. We show analyses of chiefly Hungarian linguistic data, which range from revealing complex semantic contribution of small affixes through pointing out the multiply intensional nature of certain (pre)verbs to ...
      Read Full Article
    22. A Summarization Strategy of Chinese News Discourse

      Due to the problem of information overloading, automatic text summarization is becoming more and more necessary. This paper proposes a strategy for Chinese news discourse summarization based on veins theory. This method can produce a summary of an original text without requiring its full semantic interpretation, but instead relying on the discourse structure. Content Type Book ChapterPages 389-394DOI 10.1007/978-3-642-28308-6_53Authors Deliang Wang, School of Foreign Languages and Literatures, Beijing Normal University, Beijing, China Book Series Advances in Intelligent and Soft ComputingPrint ISSN 1867-5662 Book Series Volume Volume 145/2012 Book Proceedings of the 2011 2nd International Congress on Computer ...
      Read Full Article
      Mentions: Beijing China
    23. Contested Collective Intelligence: Rationale, Technologies, and a Human-Machine Annotation Study

      Abstract  We propose the concept of Contested Collective Intelligence (CCI) as a distinctive subset of the broader Collective Intelligence design space. CCI is relevant to the many organizational contexts in which it is important to work with contested knowledge, for instance, due to different intellectual traditions, competing organizational objectives, information overload or ambiguous environmental signals. The CCI challenge is to design sociotechnical infrastructures to augment such organizational capability. Since documents are often the starting points for contested discourse, and discourse markers provide a powerful cue to the presence of claims, contrasting ideas and argumentation, discourse and rhetoric provide an annotation ...
      Read Full Article
    1-24 of 106 1 2 3 4 5 »
  1. Categories

    1. Default:

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