Multi-instance Multi-label Learning for Relation Extraction

By Mihai Surdeanu, Julie Tibshirani, Ramesh Nallapati, Christopher D. Manning. 2012

781 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Semantic Parsing on Freebase from Question-Answer Pairs (2013, background): “Sev- 8Oracle score is the fraction of examples for which D̃(x) contains any derivation with the correct denotation. eral works perform relation extraction using distant supervision from a knowledge base (Riedel et al., 2010; Carlson et al., 2010; Hoffmann et al., 2011; Surdeanu et al., 2012).”
WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia (2016, background): “, 2010), and jointly reasoning over larger sets of sentences and relations (Surdeanu et al., 2012).”
Position-aware Attention and Supervised Data Improve Slot Filling (2017, methodology): “…2003; Bunescu and Mooney, 2005), where a statistical classiﬁer is trained on an annotated dataset; second, distant supervision (Mintz et al., 2009; Surdeanu et al., 2012), where a training set is formed by projecting the relations in an existing knowledge base onto textual instances that…”
Knowledge Graph Embedding by Translating on Hyperplanes (2014, methodology): “Most existing extracting methods (Mintz et al. 2009; Riedel, Yao, and McCallum 2010; Hoffmann et al. 2011; Surdeanu et al. 2012) distantly collect evidences from an external text corpus for a candidate fact, ignoring the capability of the knowledge graph itself to reason the new fact.”
Learning Entity and Relation Embeddings for Knowledge Graph Completion (2015, methodology): “Most exiting methods (Mintz et al. 2009; Riedel, Yao, and McCallum 2010; Hoffmann et al. 2011; Surdeanu et al. 2012) take knowledge graphs as distant supervision to automatically annotate sentences in large-scale text corpora as training instances, and then extract textual features to build relation”
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (2018, background): “Adopting distant supervision is a primary approach to alleviate this problem for RC (Mintz et al.; Riedel et al.; Hoffmann et al., 2011; Surdeanu et al., 2012; Zeng et al., 2015; Lin et al., 2016), which heuristically aligns knowledge bases (KBs) and text to automatically annotate adequate amounts…”
Injecting Logical Background Knowledge into Embeddings for Relation Extraction (2015, background): “First, for canonical relations it effectively performs distant supervision (Bunescu and Mooney, 2007; Mintz et al., 2009; Yao et al., 2011; Hoffmann et al., 2011; Surdeanu et al., 2012) and hence requires no textual annotations.”
Representing Text for Joint Embedding of Text and Knowledge Bases (2015, background): “Other work proposed more sophisticated models that reason about sentence-level hidden variables (Riedel et al., 2010; Hoffmann et al., 2011; Surdeanu et al., 2012) or model the noise arising from the incompleteness of knowledge bases and text collections (Ritter et al., 2013), inter alia .”
NaturalLI: Natural Logic Inference for Common Sense Reasoning (2014, background): “Prominent examples include question answering (Voorhees, 2001), semantic parsing (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2007; Kwiatkowski et al., 2013; Berant and Liang, 2014), and information extraction systems (Hoffmann et al., 2011; Surdeanu et al., 2012).”
Ultra-Fine Entity Typing (2018, methodology): “To deal with noisy distant supervision for KB population and entity typing, researchers used multi-instance multi-label learning (Surdeanu et al., 2012; Yaghoobzadeh et al., 2017b) or custom losses (Abhishek et al., 2017; Ren et al., 2016a).”
Assessing The Factual Accuracy of Generated Text (2019, methodology): “ning, yet retain a consistent output surface form. In this paper, we consider fact classification models with fixed schema. This idea has been studied in many previous works including Surdeanu et al. [34], which considered datasets that have multiple relation labels for an entity pair, which each ma”
Towards Understanding Gender Bias in Relation Extraction (2019, background): “Great efforts have been made to improve NRE models by mitigating the effects of noise in the training data introduced by Distant Supervision (Hoffmann et al., 2011; Surdeanu et al., 2012; Lin et al., 2016; Liu et al., 2017; Feng et al., 2018; Qin et al., 2018).”
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (2019, neutral): “35 positive chains per example suggesting a multi-instance multi-label learning training setup (Surdeanu et al., 2012).”
Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks (2016, methodology): “Traditional (distantly) supervised RE methods use as input numerous lexical and syntactic features, e.g., POS tags, dependency paths, and named entity tags (Mintz et al., 2009; Riedel et al., 2010; Hoff-mann et al., 2011; Surdeanu et al., 2012).”
CORE: Context-Aware Open Relation Extraction with Factorization Machines (2015, background): “, 2012) or leverage large text corpora to learn patterns that are indicative of KB relations (Mintz et al., 2009; Surdeanu et al., 2012; Min et al., 2013).”
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2020, methodology): “, 2010) and multi-label learning (Surdeanu et al., 2012).”
Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions (2019, methodology): “Therefore, some subsequent studies (Riedel et al., 2010; Hoffmann et al., 2011; Surdeanu et al., 2012) considered distant supervision relation extraction as a multi-instance learning problem, which extracted relation from a bag of sentences instead of a single sentence.”
Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions (2017, methodology): “The probabilistic, graphical models (Riedel, Yao, and McCallum 2010; Hoffmann et al. 2011; Surdeanu et al. 2012) had considered the observation, but the features they designed to choose valid sentences are often derived from preexisting NLP tools which suffer from error propagation and accumulation ”