Matches in ScholarlyData for { ?s ?p ?o. }
- authorList hasItem item-5.
- authorList hasItem item-6.
- authorList hasItem item-7.
- authorList hasLastItem item-7.
- item-1 type ListItem.
- item-1 hasContent shigeyoshi-kitazawa.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent shinya-kiriyama.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent tomohiko-kasami.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent shogo-ishikawa.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent naofumi-otani.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent hiroaki-horiuchi.
- item-6 next item-7.
- item-6 previous item-5.
- item-7 type ListItem.
- item-7 hasContent yoichi-takebayashi.
- item-7 previous item-6.
- 239 creator emiel-krahmer.
- 239 creator jette-viethen.
- 239 creator mariet-theune.
- 239 creator pascal-touset.
- 239 creator robert-dale.
- 239 type InProceedings.
- 239 label "Controlling Redundancy in Referring Expressions".
- 239 sameAs 239.
- 239 abstract "Krahmer et al. s (2003) graph-based framework provides an elegant and flexible approach to the generation of referring expressions. In this paper, we present the first reported study that systematically investigates how to tune the parameters of the graph-based framework on the basis of a corpus of human-generated descriptions. We focus in particular on replicating the redundant nature of human referring expressions, whereby properties not strictly necessary for identifying a referent are nonetheless included in descriptions. We show how statistics derived from the corpus data can be integrated to boost the framework s performance over a non-stochastic baseline.".
- 239 hasAuthorList authorList.
- 239 hasTopic Linguistics.
- 239 isPartOf proceedings.
- 239 keyword "Evaluation methodologies".
- 239 keyword "Generation".
- 239 keyword "Statistical methods".
- 239 title "Controlling Redundancy in Referring Expressions".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent jette-viethen.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent robert-dale.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent emiel-krahmer.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent mariet-theune.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent pascal-touset.
- item-5 previous item-4.
- 24 creator florian-koehler.
- 24 creator hinrich-schuetze.
- 24 creator michaela-atterer.
- 24 type InProceedings.
- 24 label "A Question Answering System for German. Experiments with Morphological Linguistic Resources".
- 24 sameAs 24.
- 24 abstract "Question Answering systems are systems that enable the user to ask questions in natural language and to also receive an answer in natural language. Most existing systems, however, are constructed for the English language, and it is not clear in how far these approaches are also applicable to other languages. A richer morphology, greater syntactic variability, and smaller fraction of webpages available in the language are just some issues that complicate the construction of systems for German. In this paper, we present a modular Question Answering System for German which uses several morphological resources to increase recall. Nouns are converted into verbs, verbs into nouns, and the tenses of verbs are modified. We use a web search engine as a back end to allow for open-domain Question Answering. A POS-tagger is employed to identify answer candidates which are then filtered and tiled. The system is shown to achieve a higher recall than other systems for German.".
- 24 hasAuthorList authorList.
- 24 hasTopic Linguistics.
- 24 isPartOf proceedings.
- 24 keyword "Morphology".
- 24 keyword "Question Answering".
- 24 title "A Question Answering System for German. Experiments with Morphological Linguistic Resources".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent florian-koehler.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent hinrich-schuetze.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent michaela-atterer.