Learning shortest paths in word graphs

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Learning shortest paths in word graphs. / Tzouridis, Emmanouil ; Brefeld, Ulf.
Knowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013). Hrsg. / Andreas Henrich; Hans-Christian Sperker. Bamberg: Lehrstuhl für Medieninformatik - Universität Bamberg, 2014. S. 113-116.

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Tzouridis, E & Brefeld, U 2014, Learning shortest paths in word graphs. in A Henrich & H-C Sperker (Hrsg.), Knowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013). Lehrstuhl für Medieninformatik - Universität Bamberg, Bamberg, S. 113-116, Lernen, Wissen und Adaptivität - LWA 2013, Bamberg, Deutschland, 07.10.13. <http://www.minf.uni-bamberg.de/lwa2013/proceedings/proceedings_lwa1013.pdf>

APA

Tzouridis, E., & Brefeld, U. (2014). Learning shortest paths in word graphs. In A. Henrich, & H.-C. Sperker (Hrsg.), Knowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013) (S. 113-116). Lehrstuhl für Medieninformatik - Universität Bamberg. http://www.minf.uni-bamberg.de/lwa2013/proceedings/proceedings_lwa1013.pdf

Vancouver

Tzouridis E, Brefeld U. Learning shortest paths in word graphs. in Henrich A, Sperker HC, Hrsg., Knowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013). Bamberg: Lehrstuhl für Medieninformatik - Universität Bamberg. 2014. S. 113-116

Bibtex

@inbook{2330d69cb181434f90b9992748d32310,
title = "Learning shortest paths in word graphs",
abstract = "In this paper we briefly sketch our work on text summarisation using compression graphs. The task is described as follows: Given a set of related sentences describing the same event, we aim at generating a single sentence that is simply structured, easily understandable, and minimal in terms of the number of words/tokens. Traditionally, sentence compression deals with finding the shortest path in word graphs in an unsupervised setting. The major drawback of this approach is the use of manually crafted heuristics for edge weights. By contrast, we cast sentence compression as a structured prediction problem. Edges of the compression graph are represented by features drawn from adjacent nodes so that corresponding weights are learned by a generalised linear model. Decoding is performed in polynomial time by a generalised shortest path algorithm using loss augmented inference. We report on preliminary results on artificial and real world data. {\textcopyright} LWA 2013 - Lernen, Wissen and Adaptivitat, Workshop Proceedings. All rights reserved",
keywords = "Informatics, Business informatics",
author = "Emmanouil Tzouridis and Ulf Brefeld",
year = "2014",
language = "English",
pages = "113--116",
editor = "Andreas Henrich and Hans-Christian Sperker",
booktitle = "Knowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013)",
publisher = "Lehrstuhl f{\"u}r Medieninformatik - Universit{\"a}t Bamberg",
address = "Germany",
note = "Lernen, Wissen und Adaptivit{\"a}t - LWA 2013 ; Conference date: 07-10-2013 Through 09-10-2013",
url = "http://www.minf.uni-bamberg.de/lwa2013/",

}

RIS

TY - CHAP

T1 - Learning shortest paths in word graphs

AU - Tzouridis, Emmanouil

AU - Brefeld, Ulf

PY - 2014

Y1 - 2014

N2 - In this paper we briefly sketch our work on text summarisation using compression graphs. The task is described as follows: Given a set of related sentences describing the same event, we aim at generating a single sentence that is simply structured, easily understandable, and minimal in terms of the number of words/tokens. Traditionally, sentence compression deals with finding the shortest path in word graphs in an unsupervised setting. The major drawback of this approach is the use of manually crafted heuristics for edge weights. By contrast, we cast sentence compression as a structured prediction problem. Edges of the compression graph are represented by features drawn from adjacent nodes so that corresponding weights are learned by a generalised linear model. Decoding is performed in polynomial time by a generalised shortest path algorithm using loss augmented inference. We report on preliminary results on artificial and real world data. © LWA 2013 - Lernen, Wissen and Adaptivitat, Workshop Proceedings. All rights reserved

AB - In this paper we briefly sketch our work on text summarisation using compression graphs. The task is described as follows: Given a set of related sentences describing the same event, we aim at generating a single sentence that is simply structured, easily understandable, and minimal in terms of the number of words/tokens. Traditionally, sentence compression deals with finding the shortest path in word graphs in an unsupervised setting. The major drawback of this approach is the use of manually crafted heuristics for edge weights. By contrast, we cast sentence compression as a structured prediction problem. Edges of the compression graph are represented by features drawn from adjacent nodes so that corresponding weights are learned by a generalised linear model. Decoding is performed in polynomial time by a generalised shortest path algorithm using loss augmented inference. We report on preliminary results on artificial and real world data. © LWA 2013 - Lernen, Wissen and Adaptivitat, Workshop Proceedings. All rights reserved

KW - Informatics

KW - Business informatics

M3 - Article in conference proceedings

SP - 113

EP - 116

BT - Knowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013)

A2 - Henrich, Andreas

A2 - Sperker, Hans-Christian

PB - Lehrstuhl für Medieninformatik - Universität Bamberg

CY - Bamberg

T2 - Lernen, Wissen und Adaptivität - LWA 2013

Y2 - 7 October 2013 through 9 October 2013

ER -

Zuletzt angesehen

Projekte

  1. Campus Virtuell

Publikationen

  1. Formalised and Non-Formalised Methods in Resource Management-Knowledge and Social Learning in Participatory Processes
  2. Smart cities, smart borders. Sensing networks and security in the urban space
  3. Later Life Workplace Index: Validation of an English Version
  4. Fast response of groundwater to heavy rainfall
  5. Progress and challenge for magnesium alloys as biomaterials
  6. Towards a Model for Building Trust and Acceptance of Artificial Intelligence Aided Medical Assessment Systems
  7. Conditionality of EU funds: an instrument to enforce EU fundamental values?
  8. The effect of complacency potential on human operators’ monitoring behavior in aviation
  9. Exploring fruitful links between real-world laboratory and disciplinary research Introduction of the DKN Future Earth working group LinkLab
  10. Potential bias in meta-analyses of effect sizes in imaging genetics
  11. Lernen in Netzwerken
  12. Introduction to Thinking the Problematic
  13. Understanding spam
  14. Nostalgia is not what it used to be
  15. Burdens, Stresses, Resources and Needs of School Management and Teaching staff during the Corona Pandemic. Results of a qualitative Interview Study at primary and secondary Schools in Hesse
  16. Generation of 3D representative volume elements for heterogeneous materials
  17. The challenges of gamifying CSR communication
  18. The conservation against development paradigm in protected areas
  19. Cross-level Information and Influence in Mandated Participatory Planning: Alternative Pathways to Sustainable Water Management in Germany’s Implementation of the EU Water Framework Directive
  20. “The whole is greater than the sum of its parts” – Exploring teachers’ technology readiness profiles and its relation to their emotional state during COVID-19 emergency remote teaching
  21. The Change Challenge
  22. A hybrid actuator modelling and hysteresis effect identification in camless internal combustion engines control
  23. Expanding the pie or spoiling the cake? How the number of negotiation issues affects integrative bargaining
  24. Be smart, play dumb? A transactional perspective on day-specific knowledge hiding, interpersonal conflict, and psychological strain
  25. Climate-smart socially innovative tools and approaches for marine pollution science in support of sustainable development
  26. Gehen in der Datenbank – Der BMLwalker
  27. Effect of Sn additions on the age hardening response, microstructures and corrosion resistance of Mg-0.8Ca (wt%) alloys
  28. Singularities and Superintelligence
  29. Evaluation of a temporal causal model for predicting the mood of clients in an online therapy
  30. Study Protocol

Presse / Medien

  1. Too long, didn't read?