Open Information Extraction

43 papers with code • 6 benchmarks • 7 datasets

In natural language processing, open information extraction is the task of generating a structured, machine-readable representation of the information in text, usually in the form of triples or n-ary propositions (Source: Wikipedia).

Most implemented papers

OPIEC: An Open Information Extraction Corpus

uma-pi1/OPIEC AKBC 2019

In this paper, we release, describe, and analyze an OIE corpus called OPIEC, which was extracted from the text of English Wikipedia.

Relation Schema Induction using Tensor Factorization with Side Information

malllabiisc/sictf EMNLP 2016

To the best of our knowledge, this is the first application of tensor factorization for the RSI problem.

A Consolidated Open Knowledge Representation for Multiple Texts

vered1986/OKR WS 2017

We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner.

Answering Complex Questions Using Open Information Extraction

allenai/semanticilp ACL 2017

While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques.

MinIE: Minimizing Facts in Open Information Extraction

uma-pi1/minie EMNLP 2017

The goal of Open Information Extraction (OIE) is to extract surface relations and their arguments from natural-language text in an unsupervised, domain-independent manner.