Systematic comparison of neural architectures and training approaches for open information extraction
The goal of open information extraction (OIE) is to extract facts from natural language text, and to represent them as structured triples of the form (subject, predicate, object). For example, given the sentence »Beethoven composed the Ode to Joy.«, we are expected to extract the triple (Beethoven,...
Hauptverfasser: | Hohenecker, P, Mtumbuka, F, Kocijan, V, Lukasiewicz, T |
---|---|
Format: | Conference item |
Sprache: | English |
Veröffentlicht: |
Association for Computational Linguistics
2020
|
Ähnliche Einträge
Ähnliche Einträge
-
Deep neural open information extraction with background knowledge
von: Mtumbuka, FM
Veröffentlicht: (2022) -
Ontology reasoning with deep neural networks
von: Hohenecker, P, et al.
Veröffentlicht: (2020) -
Ontology reasoning with deep neural networks (extended abstract)
von: Hohenecker, P, et al.
Veröffentlicht: (2020) -
Controlling text edition by changing answers of specific questions
von: Sha, L, et al.
Veröffentlicht: (2021) -
Does the objective matter? Comparing training objectives for pronoun resolution
von: Yordanov, Y, et al.
Veröffentlicht: (2020)