Konferenzbeitrag

Towards the Detection of Reliable Food-Health Relationships

We investigate the task of detecting reliable statements about food-health relationships from natural language texts. For that purpose, we created a specially annotated web corpus from forum entries discussing the healthiness of certain food items. We examine a set of task-specific features (mostly) based on linguistic insights that are instrumental in finding utterances that are commonly perceived as reliable. These features are incorporated in a supervised classifier and compared against standard features that are widely used for various tasks in natural language processing, such as bag of words, part-of speech and syntactic parse information.

Towards the Detection of Reliable Food-Health Relationships

Urheber*in: Wiegand, Michael; Klakow, Dietrich

Free access - no reuse

0
/
0

Language
Englisch

Subject
Computerlinguistik

Event
Geistige Schöpfung
(who)
Wiegand, Michael
Klakow, Dietrich
(when)
2019-02-04
Event
Veröffentlichung
(who)
Stroudsburg, PA : Association for Computational Linguistics

URN
urn:nbn:de:bsz:mh39-84660
Last update
14.09.2023, 8:26 AM CEST

Object type


  • Konferenzbeitrag

Associated


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

Time of origin


  • 2019-02-04

Other Objects (12)