Guiding Semi-Supervision with Constraint-Driven Learning

By Ming-Wei Chang, Lev-Arie Ratinov, Dan Roth. 2007

240 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

Benefits of Intermediate Annotations in Reading Comprehension (2020, background): “Our auxiliary training with intermediate annotations is inspired by extensive related work on training models using side information or domain knowledge beyond labels (Mann and McCallum, 2008; Chang et al., 2007; Ganchev et al., 2010; Rocktaschel et al., 2015).”
Injecting Logical Background Knowledge into Embeddings for Relation Extraction (2015, methodology): “…Supervised Learning Our work is also inspired by weakly supervised approaches (Ganchev et al., 2010) that use structural constraints as a source of indirect supervision, and have been used for several NLP tasks (Chang et al., 2007; Mann and McCallum, 2008; Druck et al., 2009; Singh et al., 2010).”
Label-Free Supervision of Neural Networks with Physics and Domain Knowledge (2016, background): “Natural language processing has seen many successful applications of constraint learning [10, 2, 5], and the recent work of [12] has provided a fresh perspective on the idea of learning with labeling functions, rather than labels, in the form of Data Programming.”
Mapping to Declarative Knowledge for Word Problem Solving (2017, neutral): “More recent approaches tried to incorporate knowledge in the form of constraints or expectations from the output (Roth and tau Yih, 2004; wei Chang et al., 2007; Chang et al., 2012; Ganchev et al., 2010; Smith and Eisner, 2006; Naseem et al., 2010; Bisk and Hockenmaier, 2012; Gimpel and Bansal,…”
Generalized Expectation Criteria for Semi-Supervised Learning of Conditional Random Fields (2008, methodology): “Labeled instances are available, the technique described in CRR07 can be used.”
Posterior Regularization for Structured Latent Variable Models (2010, methodology): “Chang et al. (2007) report similar results for their constraint-driven learning framework.”
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (2019, background): “This approach is reminiscent of constraint-driven learning (Chang et al., 2007), as well as of multi-instance learning methods common in relation extraction (Riedel et al., 2010; Surdeanu et al., 2012).”
Learning from labeled features using generalized expectation criteria (2008, unknown): “Chang, Ratinov, and Roth [2] propose an EM-like algorithm that incorporates prior constraints into semi-supervised training of structured output models.”
Toward an Architecture for Never-Ending Language Learning (2010, unknown): “" Chang, Ratinov, and Roth (2007) also showed that enforcing constraints given as domain knowledge can improve semi-supervised learning.”
Semi-Supervised Learning via Generalized Maximum Entropy (2010, background): “were one of the first to guide semi-supervised algorithms with constraints (Chang et al., 2007).”
Estimating Accuracy from Unlabeled Data (2014, methodology): “Moreover, there has been work at developing more robust semi-supervised learning algorithms by using the concept of agreement rates [Collins and Singer, 1999] or some task specific constraints [Chang et al., 2007] to decide what should be added to the training data set.”
Modeling Relations and Their Mentions without Labeled Text (2010, methodology): “Our work is based on constraint-driven semi-supervised learning [6, 16].”
Confidence Driven Unsupervised Semantic Parsing (2011, methodology): “Our unsupervised approach follows a self training protocol (Yarowsky, 1995; McClosky et al., 2006; Reichart and Rappoport, 2007b) enhanced with constraints restricting the output space (Chang et al., 2007; Chang et al., 2009).”
Zero-shot Learning of Classifiers from Natural Language Quantification (2018, background): “Prominent among these are the Constraint-driven learning (Chang et al., 2007a), Generalized Expectation (Mann and McCallum, 2010) and Posterior Regularization (Ganchev et al., 2010) and Bayesian Measurements (Liang et al., 2009) frameworks.”
Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing (2015, background): “The first is a phrase-structure feature set, based on the work of Collins (2000); Charniak & Johnson (2005); Huang (2008b).”
Ontological Smoothing for Relation Extraction with Minimal Supervision (2012, background): “(Chang, Ratinov, and Roth 2007; Smith and Eisner 2005; Bellare and McCallum 2009) allow learning with soft constraints, for example in the form of labeled features.”