-
-
Autor*innen: Tzouridis, Emmanouil; Brefeld, Ulf
Titel: Learning shortest paths in word graphs
Aus: Henrich, Andreas ; Sperker, Hans-Christian (Hrsg.): LWA 2013: Lernen, Wissen & Adaptivität. Workshop Proceedings, Bamberg, 7.-9. Oktober 2013, Bamberg: KDML, 2013 , S. 113-116
URL: http://www.minf.uni-bamberg.de/lwa2013/proceedings/proceedings_lwa1013.pdf
Dokumenttyp: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Sprache: Englisch
Schlagwörter: Algorithmus; Grafische Darstellung; Informatik; Lernen; Mapping; Satz; Struktur; Wort
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.
DIPF-Abteilung: Informationszentrum Bildung