Joint Inference in Information Extraction

By Hoifung Poon, Pedro M. Domingos. AAAI Conference on Artificial Intelligence, 2007

298 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9afc2cb61a4da0aa29fa9f40889d21ff67157c7a

How researchers see this paper

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

Citations in the corpus

Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning (2016, methodology): “Instead, the proposed method utilizes external information sources to resolve ambiguities inherent in text interpretation.”
Grounded Unsupervised Semantic Parsing (2013, background): “This is in contrast with semantic role labeling (Carreras and Marquez, 2004) and information extraction (Banko et al., 2007; Poon and Domingos, 2007), which have a more restricted goal of identifying local semantic roles or extracting selected information slots.”
Statistical Relational Artificial Intelligence: Logic, Probability, and Computation (2016, methodology): “Markov logic has also been used for joint inference for event extraction [Poon and Domingos, 2007, Riedel and McCallum, 2011].”
Learning Markov Logic Networks via Functional Gradient Boosting (2011, methodology): “For learning structure using motifs, we used the settings provided by Kok and Domingos [12].”
Machine Reading at the University of Washington (2010, background): “…shown that in supervised learning, joint inference can substantially improve predictive performance on tasks related to machine reading (e.g., citation information extraction (Poon and Domingos, 2007), ontology induction (Wu and Weld, 2008), temporal information extraction (Ling and Weld, 2010)).”
StatSnowball: a statistical approach to extracting entity relationships (2009, background): “The promise of integrated extraction has been shown in different applications [20, 28].”
News events prediction using Markov logic networks (2018, methodology): “To fix the problem, joint inference [34] was proposed as a key solution.”
DeepDive: Declarative Knowledge Base Construction (2016, methodology): “Within this space, there are three styles of systems that based on classiﬁcation-based frameworks [2,3,6,12,45], maximum a posteriori (MAP) [21,29, 40], and probabilistic graphical models [10, 35, 49].”
Semi-supervised multi-task learning of structured prediction models for web information extraction (2011, methodology): “[5, 1, 29, 30, 41] apply sequential models like Hidden Markov Models (HMM), Conditional Random Fields (CRF) and Markov Logic Networks (MLN) to segment instances such as citations and addresses.”
Human-Guided Learning for Probabilistic Logic Models (2018, methodology): “We perform experiments in several standard relational domains including cora (Poon and Domingos, 2007) - a publication and citation dataset, heart - a heart attack dataset, uw (Mihalkova and Mooney, 2007) - a dataset of professors and students, and webkb (Richardson et al., 2006) - a course dataset.”
Joint Entity Resolution (2012, methodology): “) that we could have exploited and better models [19] for constructing the comparison rules.”
FACTORIE: Probabilistic Programming via Imperatively Defined Factor Graphs (2009, methodology): “The features of these templates correspond to the SimilarTitle and SimilarVenue first-order features in [21].”
Incremental Knowledge Base Construction Using DeepDive (2015, methodology): “ledge Base Construction (KBC) KBC has been an area of intense study over the last decade, moving from pattern matching [24] and rule-based systems [33,34] to systems that use machine learning for KBC [6{8, 10, 17, 18, 30, 38, 44, 51, 59, 63]. Many groups have studied how to improve the quality of sp”