-
-
Autor*innen: Tzouridis, Emmanouil; Nasir, Jamal A.; Brefeld, Ulf
Titel: Learning to summarise related sentences
Aus: Association for Computational Linguistics (Hrsg.): Proceedings of COLING 2014: Technical papers, Stroudsburg; PA: Association for Computational Linguistics, 2014 , S. 1636-1647
URL: http://www.aclweb.org/anthology/C14-1155
Dokumenttyp: 4. Beiträge in Sammelbänden; Tagungsband/Konferenzbeitrag/Proceedings
Sprache: Englisch
Schlagwörter: Abstract; Algorithmus; Automatisierung; Computerlinguistik; Datenverarbeitung; Semantik; Text
Abstract: We cast multi-sentence compression as a structured prediction problem. Related sentences are represented by a word graph so that summaries constitute paths in the graph (Filippova, 2010). We devise a parameterised shortest path algorithm that can be written as a generalised linear model in a joint space of word graphs and compressions. We use a large-margin approach to adapt parameterised edge weights to the data such that the shortest path is identical to the desired summary. Decoding during training is performed in polynomial time using loss augmented inference. Empirically, we compare our approach to the state-of-the-art in graph-based multi-sentence compression and observe significant improvements of about 7% in ROUGE F-measure and 8% in BLEU score, respectively. (DIPF/Orig.)
DIPF-Abteilung: Informationszentrum Bildung