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,...
Автори: | Hohenecker, P, Mtumbuka, F, Kocijan, V, Lukasiewicz, T |
---|---|
Формат: | Conference item |
Мова: | English |
Опубліковано: |
Association for Computational Linguistics
2020
|
Схожі ресурси
Схожі ресурси
-
Deep neural open information extraction with background knowledge
за авторством: Mtumbuka, FM
Опубліковано: (2022) -
Ontology reasoning with deep neural networks
за авторством: Hohenecker, P, та інші
Опубліковано: (2020) -
Ontology reasoning with deep neural networks (extended abstract)
за авторством: Hohenecker, P, та інші
Опубліковано: (2020) -
Controlling text edition by changing answers of specific questions
за авторством: Sha, L, та інші
Опубліковано: (2021) -
Does the objective matter? Comparing training objectives for pronoun resolution
за авторством: Yordanov, Y, та інші
Опубліковано: (2020)