Coupled semi-supervised learning for information extraction

By Andrew Carlson, Justin Betteridge, Richard C. Wang, Estevam R. Hruschka, Tom Michael Mitchell. Web Search and Data Mining, 2010

489 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/df3196bd230e23a86fbf8254daa78c7be9df028a

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

Citations in the corpus

Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, background): “Such kind of notable examples include DBpedia [1], YAGO [2], Freebase [3], KnowItAll [4], ReadTheWeb [5], and Probase [6].”
A Survey on Knowledge Graph-Based Recommender Systems (2020, background): “…Cross-Domain Wikipedia Satori [31] Cross-Domain Web Data CN-DBPedia [33] Cross-Domain Baidu Baike [38], Hudong Baike [39], Wikipedia (Chinese) NELL [24] Cross-Domain Web Data Wikidata [40] Cross-Domain Wikipedia, Freebase Google’s Knowledge Graph [18] Cross-Domain Web data Facebooks Entities Graph…”
Toward an Architecture for Never-Ending Language Learning (2010, unknown): “CPL is described in detail by Carlson et al. (2010).”
Hierarchical Semi-supervised Classification with Incomplete Class Hierarchies (2016, methodology): “Figure 1: Subsets of NELL [8] ontology used in our hierarchical classiﬁcation experiments.”
Named Entity Recognition in Tweets: An Experimental Study (2011, background): “Previous work on Semantic Bootstrapping has taken a weakly-supervised approach to classifying named entities based on large amounts of unlabeled text (Etzioni et al., 2005; Carlson et al., 2010; Kozareva and Hovy, 2010; Talukdar and Pereira, 2010; McIntosh, 2010).”
Language-Aware Truth Assessment of Fact Candidates (2014, methodology): “Second, we applied our alternative candidate generation method to discover alternatives from the Web, SVO corpus, and NELL.”
Open Information Extraction: The Second Generation (2011, background): “The Never Ending Language Learner (NELL) project aims to learn a macro-reading agent that gets better and better at reading as it reads the same text multiple times [Carlson et al., 2010a; 2010b].”
Event Schema Induction with a Probabilistic Entity-Driven Model (2013, background): “Current relation discovery (Banko et al., 2007a; Carlson et al., 2010b) focuses on atomic facts and relations.”
Injecting Logical Background Knowledge into Embeddings for Relation Extraction (2015, background): “Carlson et al. (2010) in particular is similar since they use common sense constraints to jointly train multiple information extractors.”
Rethinking Search: Making Experts out of Dilettantes (2021, methodology): “Originally assembled and curated by hand, there has been much research on automatically extracting knowledge graph triplets from Web pages, including Yago [78], NELL [12, 58], and Knowledge Vault [22].”
Exploratory Learning (2013, background): “One of our benchmark tasks, entity classification, is inspired by the NELL (Never Ending Language Learning) system [5].”
Improved Pattern Learning for Bootstrapped Entity Extraction (2014, methodology): “Carlson et al. (2010) learned multiple semantic types using coupled semi-supervised training from web-scale data, which is not feasible for all datasets and entity learning tasks.”
Multimodal Learning for Web Information Extraction (2017, methodology): “Type checking [6, 19, 22] by specifying types (e.”
Knowledge graph refinement: A survey of approaches and evaluation methods (2016, methodology): “For example, NELL and PROSPERA perform reasoning at that point to determine whether the new axiom is plausible or not, and discard implausible ones [14,69].”
A Multi-Channel Deep Neural Network for Relation Extraction (2020, background): “, latent topic variables, or positional information) to generate combined features [16]–[20].”
Never-Ending Learning (2015, methodology): “This is performed by the CML system (Carlson et al. 2010b), which represents the noun phrase by a vector with thousands of string features.”
Embedding Methods for Fine Grained Entity Type Classification (2015, background): “These types are useful for deeper natural language analysis such as coreference resolution (Recasens et al., 2013), relation extraction (Yao et al., 2010), and downstream applications such as knowledge base construction (Carlson et al., 2010) and question answering (Lin et al., 2012).”