Konferenzbeitrag

Automatic Food Categorization from Large Unlabeled Corpora and Its Impact on Relation Extraction

We present a weakly-supervised induction method to assign semantic information to food items. We consider two tasks of categorizations being food-type classification and the distinction of whether a food item is composite or not. The categorizations are induced by a graph-based algorithm applied on a large unlabeled domain-specific corpus. We show that the usage of a domain-specific corpus is vital. We do not only outperform a manually designed open-domain ontology but also prove the usefulness of these categorizations in relation extraction, outperforming state-of-the-art features that include syntactic information and Brown clustering.

Automatic Food Categorization from Large Unlabeled Corpora and Its Impact on Relation Extraction

Urheber*in: Wiegand, Michael; Roth, Benjamin; Klakow, Dietrich

Namensnennung - Nicht kommerziell - Weitergabe unter gleichen Bedingungen 4.0 International

0
/
0

Sprache
Englisch

Thema
Computerlinguistik

Ereignis
Geistige Schöpfung
(wer)
Wiegand, Michael
Roth, Benjamin
Klakow, Dietrich
(wann)
2019-02-05
Ereignis
Veröffentlichung
(wer)
Stroudsburg, PA : Association for Computational Linguistics

URN
urn:nbn:de:bsz:mh39-84696
Letzte Aktualisierung
14.09.2023, 08:26 MESZ

Objekttyp


  • Konferenzbeitrag

Beteiligte


  • Wiegand, Michael
  • Roth, Benjamin
  • Klakow, Dietrich
  • Stroudsburg, PA : Association for Computational Linguistics

Entstanden


  • 2019-02-05

Ähnliche Objekte (12)