Learning Language Semantics from Ambiguous Supervision

By Rohit J. Kate, Raymond J. Mooney. 2007

83 citations recorded by the source corpus.

Subfields: Natural Language Processing, Computational Linguistics & Semantics

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

In Computational Linguistics & Semantics

Citations in the corpus

Learning Dependency-Based Compositional Semantics (2011, background): “Since then, there has been a healthy line of work yielding increasingly more accurate semantic parsers by using new semantic representations and machine learning techniques (Zelle and Mooney, 1996; Miller et al., 1996; Tang and Mooney, 2001; Ge and Mooney, 2005; Kate et al., 2005; Zettlemoyer and Co”
Learning Semantic Correspondences with Less Supervision (2009, background): “Some recent work in the NLP community has also moved in this direction by relaxing the amount of supervision to the setting where each sentence is paired with a small set of candidate meanings (Kate and Mooney, 2007; Chen and Mooney, 2008).”
Learning to Interpret Natural Language Navigation Instructions from Observations (2011, background): “…including supervised training (Snyder and Barzilay 2007), iteratively retraining a semantic parser/language generator to disambiguate the context (Kate and Mooney 2007; Chen, Kim, and Mooney 2010), building a generative model of the content selection process (Liang, Jordan, and Klein 2009; Kim…”
Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World (2013, background): “Finally, work on grounded language acquisition leverages semantic parsing to map from natural language to a formal representation of an environment (Kate and Mooney, 2007; Chen and Mooney, 2008; Shimizu and Haas, 2009; Matuszek relation. et al., 2010; Dzifcak et al., 2009; Cantrell et al., 2010;…”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, methodology): “Kate and Mooney (2007) introduced an extension to one such system, K RISP (Kate & Mooney, 2006), so that it can learn from ambiguous training data that requires little or no human annotation effort.”
Learning to Connect Language and Perception (2008, methodology): “We enhanced our existing methods for learning semantic parsers and language generators (Kate & Mooney 2007; Wong & Mooney 2007a) in order to learn to understand and produce language from such ambiguous training data.”
Generative Alignment and Semantic Parsing for Learning from Ambiguous Supervision (2010, methodology): “WASP seems to be affected more than Lu et al.’s system by such extraneous noise. However, in tactical generation, this extraneous noise does not seem to lead to worse performance, and our approach always gives the best results. As discussed by Chen and Mooney (2008) and Chen et al.”
Semantic Understanding of Professional Soccer Commentaries (2012, background): “[Kate and Mooney, 2007] introduce an Expectation Maximization (EM) approach with weak supervision in the GeoQuery and Child corpora.”
Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences (2010, background): “Baselines The first one is Krisper (Kate & Mooney, 2007) which obtained the best results on RoboCup in (Chen & Mooney, 2008).”
Towards Understanding Situated Natural Language (2010, unknown): “…< kitchen > , and, (2) “he” only refers to a subset of concepts in u (the males). quence y given u is to consider a model of the form: where g ( · ) returns a scalar that should be a large value when the output concepts y ′ are consistent with both the sentence x and the current state of…”
Multi-Resolution Language Grounding with Weak Supervision (2014, methodology): “Following others (Liang et al., 2009; Kate and Mooney, 2007), we use string matches to determine the affinity between a word and the Player attribute.”