Bringing Machine Learning and Compositional Semantics Together
By Percy Liang, Christopher Potts. 2015
76 citations recorded by the source corpus.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Mohit Bansal
- Jacob Andreas
- Percy Liang
- Luke S. Zettlemoyer
- Tom Michael Mitchell
- Zhou Yu
- Sergey Levine
- James Y. Zou
In Natural Language Processing
- Tom Michael Mitchell
- Jacob Andreas
- Mohit Bansal
- Percy Liang
- Igor Labutov
- Jesse Thomason
- Mirella Lapata
- Raymond J. Mooney
Citations in the corpus
- ALICE: Active Learning with Contrastive Natural Language Explanations (2020, methodology): “We implement our semantic parser on top of the Pythonbased SippyCup (Liang and Potts, 2015) following previous work Hancock et al. (2018).”
- Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, methodology): “Following recent work in semantic parsing (Liang and Potts, 2015; Krishnamurthy and Mitchell, 2012), we use a log-linear model over logical forms: where φ ( s, l ) ∈ R d is a feature vector over statements s and logical interpretations l .”
- Implicit Representations of Meaning in Neural Language Models (2021, methodology): “To determine whether the advantage is conferred by LM pretraining or fine-tuning, we ablate either open-domain pretraining, in a -pretrain,+fine-tune ablation, or in-domain fine-tuning, in a +pretrain,-fine-tune ablation.”
- Learning executable semantic parsers for natural language understanding (2016, neutral): “As we discussed earlier, parameter estimation can be performed by stochastic gradient descent on the log-likelihood; similar objectives based on max-margin are also possible [22].”
- Jointly Improving Parsing and Perception for Natural Language Commands through Human-Robot Dialog (2020, methodology): “In the interest of space, we refer the reader to other work in learning statistical parsers for details [22].”
- SQLizer: query synthesis from natural language (2017, methodology): “As a first step, our method uses standard semantic parsing techniques [Kate and Mooney 2006; Kate et al. 2005; Liang and Potts 2015] from the NLP community to translate the user’s English description into a so-called query sketch (skeleton) .”