Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
105
Learning to Map Text to Graph-based Meaning Representations via Grammar Induction
"... We argue in favor of using a graph-based representation for language meaning and propose a novel learning method to map natural language text to its graph-based meaning representation. We present a grammar formalism, which combines syntax and semantics, and has ontology constraints at the rule level ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
level. These constraints establish links between language expressions and the entities they refer to in the real world. We present a relational learning algorithm that learns these grammars from a small representative set of annotated examples, and show how this grammar induction framework
Loopy Belief Propagation for Large-Scale Collective Entity Linking
, 2014
"... Entity linking, a very popular research topic nowadays, involves identi-fying mentions of ‘real world ’ entities in natural language text and asso-ciating them with a representation from a knowledge thesaurus. It is a form of semantic grounding of discourse in a background repository of world knowle ..."
Abstract
- Add to MetaCart
Entity linking, a very popular research topic nowadays, involves identi-fying mentions of ‘real world ’ entities in natural language text and asso-ciating them with a representation from a knowledge thesaurus. It is a form of semantic grounding of discourse in a background repository of world
Materials for an exploratory theory of the network society.
- The British Journal of Sociology
, 2000
"... ABSTRACT This article aims at proposing some elements for a grounded theor y of the network society. The network society is the social structure characteristic of the Information Age, as tentatively identi ed by empirical, cross-cultural investigation. It permeates most societies in the world, in v ..."
Abstract
-
Cited by 122 (0 self)
- Add to MetaCart
;real virtuality'. Our symbolic environment is, by and large, structured by this exible, inclusive hypertext, in which many people surf each day. The virtuality of this text is in fact a fundamental dimension of reality, providing the symbols and icons from which we think and thus exist. This growing
One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations
"... Discourse relations bind smaller linguis-tic units into coherent texts. However, automatically identifying discourse rela-tions is difficult, because it requires un-derstanding the semantics of the linked ar-guments. A more subtle challenge is that it is not enough to represent the meaning of each a ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
argument of a discourse relation, because the relation may depend on links between lower-level components, such as entity mentions. Our solution computes distributional meaning representations by composition up the syntactic parse tree. A key difference from previous work on compositional distributional
Hierarchical Multi-Label Classification of Social Text Streams
"... Hierarchical multi-label classification assigns a document to mul-tiple hierarchical classes. In this paper we focus on hierarchical multi-label classification of social text streams. Concept drift, com-plicated relations among classes, and the limited length of docu-ments in social text streams mak ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
make this a challenging problem. Our approach includes three core ingredients: short document expan-sion, time-aware topic tracking, and chunk-based structural learn-ing. We extend each short document in social text streams to a more comprehensive representation via state-of-the-art entity link-ing
press-a). An overview of DR-LINK and its approach to document filtering
- Proceedings of the Hmnan Langtlage Technology Workshon
, 1993
"... DR-LINK is an information retrieval system, complex in design and processing, with the potential for providing significant advances in retrieval results due to the range and richness of semantic representation done by the various modules in the system. By using a full continuum of linguistic-concept ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(e.g. Subject Field Codes, proper noun categories, discourse components, concept-relation-concept triples, Conceptual Graphs) added to the basic text, is the real attention paid to representation at a deeper than surface level. That is, DR-LINK deals with lexical entities via conceptually
The role of friends' appearance and behavior on evaluations of individuals on Facebook: Are we known by the company we keep?.
- Human Communication Research,
, 2008
"... This research explores how cues deposited by social partners onto one's online networking profile affect observers' impressions of the profile owner. An experiment tested the relationships between both (a) what one's associates say about a person on a social network site via '&a ..."
Abstract
-
Cited by 65 (0 self)
- Add to MetaCart
variations raise new questions about interpersonal impressions. For example, with people meeting via text-based CMC-e-mail, discussion groups, or chat spaces of various kinds-a variety of questions arose about impression formation and management. These included whether and at what rate impressions are formed
Combining information extraction, deductive reasoning and machine learning for relation prediction
- IN: PROCEEDINGS OF THE ESWC (2012
"... Three common approaches for deriving or predicting instantiated relations are information extraction, deductive reasoning and machine learning. Information extraction uses subsymbolic unstructured sensory information, e.g. in form of texts or images, and extracts statements using various methods ra ..."
Abstract
-
Cited by 5 (4 self)
- Add to MetaCart
Three common approaches for deriving or predicting instantiated relations are information extraction, deductive reasoning and machine learning. Information extraction uses subsymbolic unstructured sensory information, e.g. in form of texts or images, and extracts statements using various methods
Cross-Modal Similarity Learning via Pairs, Preferences, and Active Supervision
"... We present a probabilistic framework for learning pair-wise similarities between objects belonging to differ-ent modalities, such as drugs and proteins, or text and images. Our framework is based on learning a binary code based representation for objects in each modal-ity, and has the following key ..."
Abstract
- Add to MetaCart
-modal similarity learning do not have such a mechanism), and (iii) the binary code length is learned from the data. We demonstrate the effectiveness of the proposed approach on two problems that require computing pairwise sim-ilarities between cross-modal object pairs: cross-modal link prediction in bipartite
Markov Logic
"... Most real-world machine learning problems have both statistical and relational aspects. Thus learners need representations that combine probability and relational logic. Markov logic accomplishes this by attaching weights to first-order formulas and viewing them as templates for features of Markov ..."
Abstract
-
Cited by 11 (1 self)
- Add to MetaCart
applied to problems in entity resolution, link prediction, information extraction and others, and is the basis of the open-source Alchemy system.
Results 1 - 10
of
105
