• Corpus ID: 10318045

Identifying Relations for Open Information Extraction

  title={Identifying Relations for Open Information Extraction},
  author={Anthony Fader and Stephen Soderland and Oren Etzioni},
Open Information Extraction (IE) is the task of extracting assertions from massive corpora without requiring a pre-specified vocabulary. [] Key Method We implemented the constraints in the ReVerb Open IE system, which more than doubles the area under the precision-recall curve relative to previous extractors such as TextRunner and woepos. More than 30% of ReVerb's extractions are at precision 0.8 or higher---compared to virtually none for earlier systems. The paper concludes with a detailed analysis of…

Figures and Tables from this paper

Open Language Learning for Information Extraction

Open Information Extraction (IE) systems extract relational tuples from text, without requiring a pre-specified vocabulary, by identifying relation phrases and associated arguments in arbitrary

Open Information Extraction: The Second Generation

The second generation of Open IE systems are described, which rely on a novel model of how relations and their arguments are expressed in English sentences to double precision/recall compared with previous systems such as TEXTRUNNER and WOE.

Open Information Extraction

This paper describes an overview of two Open IE generations including strengths, weaknesses and application areas and exposes simple yet principled ways in which verbs express relationships in linguistics such as verb phrase- based extraction or clause-based extraction.

Open Information Extraction Based on Lexical-Syntactic Patterns

A novel Open IE approach that performs unsupervised extraction of triples by applying a few lexical-syntactic patterns to POS-tagged texts is described, overcoming those from the state-of-the-art systems.

Open Information Extraction Systems and Downstream Applications

  • Mausam
  • Computer Science
  • 2016
A decade of progress on building Open IE extractors is described, which results in the latest extractor, OPENIE4, which is computationally efficient, outputs n-ary and nested relations, and also outputs relations mediated by nouns in addition to verbs.

Extraction Systems and Downstream Applications

A decade of progress on building Open IE extractors is described, which results in the latest extractor, OPENIE4, which is computationally efficient, outputs n-ary and nested relations, and also outputs relations mediated by nouns in addition to verbs.

Improving Open Relation Extraction via Sentence Re-Structuring

The proposed approach replaces complex sentences by several others that, together, convey the same meaning and are more amenable to extraction by current ORE systems, and succeeds in reducing the processing time and increasing the accuracy of the state-of-the-art ORE Systems.

Improving Open Information Extraction Using Domain Knowledge

This paper proposes to handle parsing errors before doing OIE itself, and shows how the MWE-problem can be handle in a given domain and how Mwe-unbreakable property is a good filter for OIE.

Nested Propositions in Open Information Extraction

NESTIE is proposed, which uses a nested representation to extract higher-order relations, and complex, interdependent assertions, and Nesting the extracted propositions allows NESTIE to more accurately reflect the meaning of the original sentence.

A Language Model for Extracting Implicit Relations

IMPLIE (Implicit relation Information Extraction) is presented, that uses an open-domain syntactic language model and user-supplied semantic taggers to overcome this limitation of implicit relations.



Open Information Extraction Using Wikipedia

WOE is presented, an open IE system which improves dramatically on TextRunner's precision and recall and is a novel form of self-supervised learning for open extractors -- using heuristic matches between Wikipedia infobox attribute values and corresponding sentences to construct training data.

Semantic Role Labeling for Open Information Extraction

This work investigates the use of semantic features (semantic roles) for the task of Open IE and finds that SRL-IE is robust to noisy heterogeneous Web data and outperforms TextRunner on extraction quality.

The Tradeoffs Between Open and Traditional Relation Extraction

A new model for Open IE called O-CRF is presented and it is shown that it achieves increased precision and nearly double the recall than the model employed by TEXTRUNNER, the previous stateof-the-art Open IE system.

Open Information Extraction from the Web

Open IE (OIE), a new extraction paradigm where the system makes a single data-driven pass over its corpus and extracts a large set of relational tuples without requiring any human input, is introduced.

Adapting Open Information Extraction to Domain-Specific Relations

The steps needed to adapt Open IE to a domain-specific ontology are explored and the approach of mapping domain-independent tuples to an ontology using domains from DARPA’s Machine Reading Project is demonstrated.

Preemptive Information Extraction using Unrestricted Relation Discovery

A technique called Unrestricted Relation Discovery is proposed that discovers all possible relations from texts and presents them as tables in order to extend the boundary of Information Extraction systems.

Learning Information Extraction Rules for Semi-Structured and Free Text

WHISK is designed to handle text styles ranging from highly structured to free text, including text that is neither rigidly formatted nor composed of grammatical sentences, and can also handle extraction from free text such as news stories.

A hybrid approach for extracting semantic relations from texts

It is suggested that the use of knowledge intensive strategies to process the input text and corpusbased techniques to deal with unpredicted cases and ambiguity problems allows to accurately discover the relevant relations between pairs of entities in that text.

Identifying Functional Relations in Web Text

Leibniz is utilized to generate the first public repository of automatically-identified functional relations, exploiting the synergy between the Web corpus and freely-available knowledge resources such as Free-base to solve the challenge of determining whether a textual phrase denotes a functional relation.

Learning 5000 Relational Extractors

LUCHS is presented, a self-supervised, relation-specific IE system which learns 5025 relations --- more than an order of magnitude greater than any previous approach --- with an average F1 score of 61%.