Learning shortest paths in word graphs

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

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
Original languageEnglish
Title of host publicationKnowledge Discovery, Data Mining and Machi- ne Learning (KDML-2013)
EditorsAndreas Henrich, Hans-Christian Sperker
Number of pages4
Place of PublicationBamberg
PublisherLehrstuhl für Medieninformatik - Universität Bamberg
Publication date2014
Pages113-116
Publication statusPublished - 2014
Externally publishedYes
EventLernen, Wissen und Adaptivität - LWA 2013 - Bamberg, Germany
Duration: 07.10.201309.10.2013
http://www.minf.uni-bamberg.de/lwa2013/

Recently viewed

Publications

  1. A Decoupled MPC for Motion Control in Robotino Using a Geometric Approach
  2. Switching Dispatching Rules with Gaussian Processes
  3. A direct test of the similarity assumption — Focusing on differences as compared with similarities decreases automatic imitation
  4. Student Game Design for Language Learning
  5. The Relation of Children's Performances in Spatial Tasks at Two Different Scales of Space
  6. Serendipity as a Mechanism of Change and its Potential for Explaining Change Processes
  7. An empirically grounded ontology for analyzing IT-based interventions in business ecosystems
  8. Internet-based public debate of CCS
  9. Enhancing Community Interactions with Data-Driven Chatbots - The DBpedia Chatbot
  10. Are criminals better lie detectors? Investigating offenders' abilities in the context of deception detection
  11. Comparison of three methods of length compensation in a parallel kinematic and their equivalence conditions
  12. Offline question answering over linked data using limited resources
  13. Phase Shift APOD and POD Control Technique in Multi-Level Inverters to Mitigate Total Harmonic Distortion
  14. Does isolation affect phenotypic variability and fluctuating asymmetry in the endangered Red Apollo?
  15. Short and long-term dominance of negative information in shaping public energy perceptions
  16. Model and Validation of the Electromagnetic Interference Produced by Power Transmission Lines in Robotic Systems
  17. Survey on challenges of Question Answering in the Semantic Web
  18. Nonlinear anisotropic boundary value problems – regularity results and multiscale discretizations
  19. Determining Lot Sizes in Production Areas
  20. Digital Business Transformation and the Changing Role of the IT Function
  21. Predicate‐based model of problem‐solving for robotic actions planning
  22. An antisaturating adaptive preaction and a slide surface to achieve soft landing control for electromagnetic actuators
  23. Toward Data-Driven Analyses of Electronic Text Books
  24. Where pragmatics and dialectology meet: Introducing variational pragmatics
  25. Achieving enhanced mechanical properties in Mg-Gd-Y-Zn-Mn alloy by altering dynamic recrystallization behavior via pre-ageing treatment
  26. An isomorphism between polynomial eigenfunctions of the transfer operator and the Eichler cohomology for modular groups