University of Groningen
Character-based Neural Semantic Parsing van Noord, Rik
DOI:
10.33612/diss.169308968
IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below.
Document Version
Publisher's PDF, also known as Version of record
Publication date: 2021
Link to publication in University of Groningen/UMCG research database
Citation for published version (APA):
van Noord, R. (2021). Character-based Neural Semantic Parsing. University of Groningen. https://doi.org/10.33612/diss.169308968
Copyright
Other than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons).
Take-down policy
If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.
Downloaded from the University of Groningen/UMCG research database (Pure): http://www.rug.nl/research/portal. For technical reasons the number of authors shown on this cover page is limited to 10 maximum.
1. A potential way to improve human-computer communication is to automatically assign meaning representations to natural language texts.
2. Neural networks, and in particular sequence-to-sequence models, can produce high-quality meaning representations without using any lexical or syntactic resources.
3. The performance of the sequence-to-sequence models can nevertheless be improved by injecting linguistic knowledge. 4. The best input representation for these sequence-to-sequence models is a sequence of characters, not words.
5. To achieve better performance, the variables in the meaning representations should be rewritten to a representation based on the order of their introduction.
6. Semantic parsers that use contextual embeddings can still be improved by exploiting character-level representations.
7. Never utter an ambiguous sentence to a table full of
(computational) semanticists if you want to get any work done in the next few hours.
8. "Je bent nooit te oud om te leren dat je moet leren" - Bassie
