Learning to Extract Relations from the Web using Minimal Supervision

By Razvan C. Bunescu, Raymond J. Mooney. 2007

322 citations recorded by the source corpus.

Subfields: 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 Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Snorkel: Rapid Training Data Creation with Weak Supervision (2017, background): “The most popular form is distant supervision, in which the records of an external knowledge base are heuristically aligned with data points to produce noisy labels [4, 7, 32].”
Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, positive): “, 2019) and relation extraction have observed similar results (Bunescu and Mooney, 2007; Hancock et al., 2018; Ratner et al., 2017).”
Distant supervision for relation extraction without labeled data (2009, methodology): “A third approach has been to use a very small number of seed instances or patterns to do bootstrap learning (Brin, 1998; Riloff and Jones, 1999; Agichtein and Gravano, 2000; Ravichandran and Hovy, 2002; Etzioni et al., 2005; Pennacchiotti and Pantel, 2006; Bunescu and Mooney, 2007; Rozenfeld and Fel”
Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “…2014; Nguyen and Grishman, 2015; dos Santos et al., 2015; Xu et al., 2015; Liu et al., 2015; Miwa and Bansal, 2016) and distantly supervised models (Bunescu and Mooney, 2007; Mintz et al., 2009; Riedel et al., 2010; Hoffmann et al., 2011; Zeng et al., 2015; Lin et al., 2016; Han et al., 2018a;…”
Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths (2015, background): “…classiﬁcation approaches and models, other related research trends include information extraction from Web documents in a semi-supervised manner (Bunescu and Mooney, 2007; Banko et al., 2007), dealing with small datasets without enough labels by distant super-vision techniques (Mintz et al.,…”
Data Programming: Creating Large Training Sets, Quickly (2016, background): “There is also a wealth of examples where additional heuristic patterns used to label training data are collected from unlabeled data [6] or directly from users [19,27], in a similar manner to our approach, but without a framework to deal with the fact that said labels are explicitly noisy.”
Neural Snowball for Few-Shot Relation Learning (2019, background): “Bunescu and Mooney (2007); Mintz et al. (2009) propose distant supervision to automatically generate relation labels by aligning entities between corpora and KGs.”
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (2019, methodology): “Both the training and test sets of the original FewRel dataset are constructed by manually annotating the distantly supervised (Bunescu and Mooney, 2007; Mintz et al., 2009) results on Wikipedia corpus and Wikidata (Vrandeˇci´c and Kr¨otzsch, 2014) knowledge bases.”
Multiple instance learning: A survey of problem characteristics and applications (2016, methodology): “While some of these characteristics have been partially analyzed in the literature [10, 11, 24, 25], a formal definition of key MIL problem characteristics has yet to be described.”
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data (2016, background): “Using weak supervision to eﬃciently label training data is a popular approach, relying on methods like distant supervision [5, 18], multi-instance learning [22, 13], heuristic patterns [11, 4], user input [25, 26, 19], and crowdsourcing [9].”
Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations (2011, background): “Bunescu and Mooney (2007) connect weak supervision with multi-instance learning and extend their relational extraction kernel to this context.”
Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences (2018, background): “There is considerable research on using indirect or weak supervision to train machine learning models for image and natural language tasks without relying entirely on manually labeled data [9,15,16].”
Multi-instance Multi-label Learning for Relation Extraction (2012, background): “One of the most promising approaches to IE that addresses this limitation is distant supervision, which generates training data automatically by aligning a database of facts with text (Craven and Kumlien, 1999; Bunescu and Mooney, 2007).”
Modeling Relations and Their Mentions without Labeled Text (2010, methodology): “3 In the works of [18,3,8], relation extraction is understood somewhat differently.”
Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks (2017, methodology): “Distant supervision methods (Bunescu and Mooney, 2007; Mintz et al., 2009; Riedel et al., 2010; Yao et al., 2010; Zeng et al., 2015) address this problem partially by means of aligning text patterns with KB.”
Neural Relation Extraction with Selective Attention over Instances (2016, background): “(Bunescu and Mooney, 2007) connects weak supervision with multi-instance learning and extends it to relation extraction.”
Knowledge Graphs (2020, unknown): “Other learning-based approaches again use bootstrapping [78, 148] and distant supervision [244, 355, 439, 486, 511, 565] to forgo the need for manual labelling; the former requires a subset of manually-labelled seed examples, while the latter finds sentences in a large corpus of text mentioning pair”
Fidelity-Weighted Learning (2017, background): “…or noisy labels can be leveraged by employing a particular architecture or deﬁning a proper loss function to avoid over-ﬁtting to imperfections of the training data (Dehghani et al., 2017b; Vahdat, 2017; Patrini et al., 2017; Beigman & Klebanov, 2009; Zeng et al., 2015; Bunescu & Mooney, 2007).”