Building a Semantic Parser Overnight
Citations Over TimeTop 1% of 2015 papers
Abstract
How do we build a semantic parser in a new domain starting with zero training examples? We introduce a new methodology for this setting: First, we use a simple grammar to generate logical forms paired with canonical utterances. The logical forms are meant to cover the desired set of compositional operators, and the canonical utterances are meant to capture the meaning of the logical forms (although clumsily). We then use crowdsourcing to paraphrase these canonical utterances into natural utterances. The resulting data is used to train the semantic parser. We further study the role of compositionality in the resulting paraphrases. Finally, we test our methodology on seven domains and show that we can build an adequate semantic parser in just a few hours.
Related Papers
- → Software visualization of LR parsing and synthesized attribute evaluation(1999)8 cited
- → Top-down parsing in Coco-2(1991)4 cited
- Cetus - An Extensible Compiler Infrastructure for Source-to-Source Transformation(2003)
- → A Hybrid Approach to Parsing Natural Languages(2016)1 cited
- → Context parsing (not only) of the object-file-format description language(2013)