Open Information Extraction: The Second Generation

By Oren Etzioni, Anthony Fader, Janara Christensen, Stephen Soderland, Mausam. 2011

527 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Long Short-Term Memory-Networks for Machine Reading (2016, background): “, 2013), to fact and relation extraction (Etzioni et al., 2011; Fader et al., 2011), ontology learning (Poon and Domingos, 2010), and textual entailment (Dagan et al.”
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models (2021, background): “In fact, the broader literature on automatic knowledge graph construction has shown, time and again, that machine-authored knowledge graphs do not match the quality of human-authored knowledge graphs (Etzioni et al., 2011; Mitchell et al., 2015; Bollacker et al., 2008).”
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (2019, background): “Other work in information extraction can also be applied to knowledge base construction with open-text entities (Soderland et al., 2010; Etzioni et al., 2011; Fader et al., 2011; Mausam et al., 2012; Fan et al., 2010; Cui et al., 2018), but these methods typically extract explicitly stated text rela”
Never-Ending Learning (2015, background): “…coupling constraints C = { 〈 φ k , V k 〉 } among the solutions to these learning tasks, where φ k is a real-valued function over two or more learning tasks, specifying the degree of satisfaction of the constraint, and V k is a vector of indices over learning tasks, specifying the arguments to φ k .”
Explicit Knowledge-based Reasoning for Visual Question Answering (2015, background): “, YAGO [22, 28], OpenIE [3, 14, 15], NELL [9], NEIL [10, 11]).”
Learning Knowledge Graphs for Question Answering through Conversational Dialog (2015, background): “Open Information Extraction (Etzioni et al., 2011) avoids fixed ontologies with domain-independent linguistic features, distant supervision, and redundancy, but requires web-scale text and doesn’t improve with interaction.”
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning (2016, methodology): “Open Information Extraction Existing work in open IE has used external sources from the web to improve extraction accuracy and coverage (Agichtein and Gravano, 2000; Etzioni et al., 2011; Fader et al., 2011; Wu and Weld, 2010).”
FVQA: Fact-Based Visual Question Answering (2016, background): “, YAGO [28, 33], OpenIE [24, 34, 35], NELL [26], NEIL [27, 36], WebChild [37,38], ConceptNet [39]).”
A Review of Relational Machine Learning for Knowledge Graphs (2015, background): “• In schema-free approaches, entities and relations are identified using open information extraction (OpenIE) techniques [37], and represented via normalized but not disambiguated strings (also referred to as surface names).”
WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference (2018, methodology): “In terms of automatic generation, though relations are often represented as < subject, relation, argument > triples, Yin et al. (2015) create a large table containing 120M n-tuple relations using OpenIE (Etzioni et al., 2011), arguing that the extra expressivity afforded by these more detailed relat”
Using Structured Events to Predict Stock Price Movement: An Empirical Investigation (2014, methodology): “In contrast, we extract structured events by leveraging Open Information Extraction technology (Open IE; Yates et al. (2007); Etzioni et al. (2011); Faber et al. (2011)) without predeﬁned event types, which can effectively solve the two problems above.”
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning by Adam Yala (2017, methodology): “Existing work in open IE has used external sources from the web to improve extraction accuracy and coverage [1, 7, 8, 21].”
Neural Open Information Extraction (2018, methodology): “Following these efforts, the second generation known as R2A2 (Etzioni et al., 2011) was developed based on REVERB and an argument identifier, ARGLEARNER, to better extract the arguments for the relation phrases.”
Learning Common Sense through Visual Abstraction (2015, methodology): “We then run the ReVerb [12] information extraction tool on the captions for these images (images are not involved anymore), along with some post-processing (described in supplementary) to obtain a set of ( t P , t R , t S ) tuples, where t P is the primary noun, t R is the relation, and t S is the…”
Open Language Learning for Information Extraction (2012, background): “However, the state-of-the-art Open IE systems, REVERB (Fader et al., 2011; Etzioni et al., 2011) and WOEparse (Wu and Weld, 2010) suffer from two key drawbacks.”
Biperpedia: An Ontology for Search Applications (2014, background): “Second, additional attributes enable extracting facts from Web text using open information extraction techniques [9].”
Commonsense reasoning and commonsense knowledge in artificial intelligence (2015, background): “For example in the Open Information Extraction system 10 (Etizoni, Fader, Christensen, Soderland, & Mausam, 2011) the query "What is made of wood?"”