Menü Überspringen
Kontakt
Presse
Deutsch
English
Not track
Datenverarbeitung
Suche
Anmelden
DIPF aktuell
Forschung
Infrastrukturen
Institut
Zurück
Kontakt
Presse
Deutsch
English
Not track
Datenverarbeitung
Suche
Startseite
>
Forschung
>
Publikationen
>
Publikationendatenbank
Ergebnis der Suche in der DIPF Publikationendatenbank
Ihre Abfrage:
(Schlagwörter: "Natürlichsprachiges System")
zur erweiterten Suche
Suchbegriff
Nur Open Access
Suchen
Markierungen aufheben
Alle Treffer markieren
Export
2
Inhalte gefunden
Alle Details anzeigen
Language processing and knowledge in the web. Proceedings of the 25th International Conference of […]
Gurevych, Iryna; Biemann, Chris; Zesch, Torsten (Hrsg.)
Sammelband
| Berlin: Springer | 2013
34045 Endnote
Herausgeber*innen:
Gurevych, Iryna; Biemann, Chris; Zesch, Torsten
Titel:
Language processing and knowledge in the web. Proceedings of the 25th International Conference of the German Society for Computational Linguistics (GSCL 2013)
Erscheinungsvermerk:
Berlin: Springer, 2013 (Lecture Notes in Computer Science, 4678)
DOI:
10.1007/978-3-642-40722-2
URL:
https://link.springer.com/book/10.1007%2F978-3-642-40722-2
Dokumenttyp:
2. Herausgeberschaft; Sammelband (keine besondere Kategorie)
Sprache:
Englisch
Schlagwörter:
Computerlinguistik; Mehrsprachigkeit; Natürlichsprachiges System; Tagungsbericht
Abstract:
This book constitutes the refereed conference proceedings of the First International Conference on Language Processing and Knowledge in the Web, GSCL 2013, held in Darmstadt, Germany, in September 2013. The 20 revised full papers were carefully selected from numerous submissions and cover topics on language processing and knowledge in the Web on several important dimensions, such as computational linguistics, language technology, and processing of unstructured textual content in the Web.
DIPF-Abteilung:
Informationszentrum Bildung
Cross-genre and cross-domain detection of semantic uncertainty
Szarvas, György; Vincze, Veronika; Farkas, Richárd; Móra, György; Gurevych, Iryna
Zeitschriftenbeitrag
| In: Computational Linguistics Journal | 2012
32810 Endnote
Autor*innen:
Szarvas, György; Vincze, Veronika; Farkas, Richárd; Móra, György; Gurevych, Iryna
Titel:
Cross-genre and cross-domain detection of semantic uncertainty
In:
Computational Linguistics Journal, 38 (2012) 2, S. 335-367
URL:
http://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00098
Dokumenttyp:
3a. Beiträge in begutachteten Zeitschriften; Beitrag in Sonderheft
Sprache:
Englisch
Schlagwörter:
Computerlinguistik; Computerunterstütztes Verfahren; Information; Information Retrieval; Klassifikation; Modell; Natürlichsprachiges System; Semantik; Sprachanalyse; Textanalyse; Wissenschaftsdisziplin
Abstract (english):
Uncertainty is an important linguistic phenomenon that is relevant in various Natural Language Processing applications, in diverse genres from medical to community generated, newswire or scientific discourse and domains from science to humanities. The semantic uncertainty of a proposition can be identified in most cases by using a finite dictionary - i.e. lexical cues - and the key steps of uncertainty detection in an application include the steps of locating the (genre- and domain-specific) lexical cues, disambiguating them, and linking them with the units of interest for the particular application (e.g. identified events in information extraction). In this study, we focus on the genre and domain differences of the context-dependent semantic uncertainty cue recognition task. We introduce a unified subcategorization of semantic uncertainty as different domain applications can apply different uncertainty categories. Based on this categorization, we normalized the annotation of three corpora and present results with a state-of-the-art uncertainty cue recognition model for four fine-grained categories of semantic uncertainty. Our results reveal the domain and genre dependence of the problem; nevertheless, we also show that even a distant source domain dataset can contribute to the recognition and disambiguation of uncertainty cues, efficiently reducing the annotation costs needed to cover a new domain. Thus, the unified subcategorization and domain adaptation for training the models offer an efficient solution for cross-domain and cross-genre semantic uncertainty recognition.
DIPF-Abteilung:
Informationszentrum Bildung
Markierungen aufheben
Alle Treffer markieren
Export