A Functionality-Driven Process for Rapidly Building Semantic Parsers
Abstract/Contents
- Abstract
- Imagine being able to build and train a parser over any domain of knowledge, starting from zero training data, over the course of a few hours. In this thesis, my research goal is to develop a new functionality-driven methodology in an attempt to achieve this. My attempt uses a domain-general grammar and a domain-specific seed lexicon to generate logical forms paired with canonical utter- ances that capture the meaning of the logical forms. By construction, the domain-general grammar ensures complete coverage of the desired set of compositional operators. I then use crowdsourcing to paraphrase these canonical utterances into natural utterances. The resulting data is used to train the semantic parser. I further study the role of compositionality in the resulting paraphrases. Finally, I test our methodology on eight domains and show that I can build an adequate semantic parser in just a few hours.
Description
| Type of resource | text |
|---|---|
| Date created | May 19, 2015 |
Creators/Contributors
| Author | Wang, Yushi |
|---|---|
| Degree granting institution | Stanford University. Department of Computer Science. |
Subjects
| Subject | semantic parsing |
|---|---|
| Subject | natural language processing |
| Subject | computer science |
| Genre | Thesis |
Bibliographic information
| Related Publication | Y. Wang, J. Berant, and P. Liang. Building a semantic parser overnight. In Association for Computational Linguistics (ACL), 2015. |
|---|---|
| Related item | |
| Location | https://purl.stanford.edu/rs367fg5533 |
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Preferred citation
- Preferred Citation
- Wang, Yushi (5/19). A Functionality-Driven Process for Rapidly Building Semantic Parsers. Stanford Digital Repository. Available at: http://purl.stanford.edu/rs367fg5533
Collection
Undergraduate Theses, School of Engineering
View other items in this collection in SearchWorksContact information
- Contact
- yushiw@cs.stanford.edu
Also listed in
Loading usage metrics...